{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/speech-emotion-recognition/papers/4","list_of":"/task/speech-emotion-recognition","task":"Speech Emotion Recognition","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":5,"rows_per_page":100,"rows":[301,400],"of":431,"counts":{"archive_papers_tagged":431,"with_a_code_link":139,"where_syntology_ran_a_sample":15,"not_listed_spam_title":0,"listed":431,"listed_where_code_ran":15,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":14,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":14,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/speech-emotion-recognition","prev":"/task/speech-emotion-recognition/papers/3","next":"/task/speech-emotion-recognition/papers/5","papers":[{"url":null,"slug":"feature-selection-enhancement-and-feature","title":"Feature Selection Enhancement and Feature Space Visualization for Speech-Based Emotion Recognition","date":"2022-08-19","arxiv_id":"2208.09269","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-contrastive-self-supervised-learning-for","title":"Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech","date":"2022-08-10","arxiv_id":"2208.05445","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-speech-emotion-recognition-using-1","title":"Multimodal Speech Emotion Recognition using Cross Attention with Aligned Audio and Text","date":"2022-07-26","arxiv_id":"2207.12895","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctl-mtnet-a-novel-capsnet-and-transfer","title":"CTL-MTNet: A Novel CapsNet and Transfer Learning-Based Mixed Task Net for the Single-Corpus and Cross-Corpus Speech Emotion Recognition","date":"2022-07-18","arxiv_id":"2207.10644","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-cross-lingual-speech-emotion","title":"Semi-supervised cross-lingual speech emotion recognition","date":"2022-07-14","arxiv_id":"2207.06767","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adapting-speech-emotion-recognition","title":"Domain Adapting Deep Reinforcement Learning for Real-world Speech Emotion Recognition","date":"2022-07-07","arxiv_id":"2207.12248","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cross-corpus-study-on-speech-emotion","title":"A cross-corpus study on speech emotion recognition","date":"2022-07-05","arxiv_id":"2207.02104","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-isomorphism-network-with-weighted","title":"A Graph Isomorphism Network with Weighted Multiple Aggregators for Speech Emotion Recognition","date":"2022-07-03","arxiv_id":"2207.00940","repositories_listed":0,"syntology":null},{"url":null,"slug":"speecheq-speech-emotion-recognition-based-on","title":"SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning","date":"2022-06-27","arxiv_id":"2206.13101","repositories_listed":0,"syntology":null},{"url":null,"slug":"multitask-vocal-burst-modeling-with-resnets","title":"Multitask vocal burst modeling with ResNets and pre-trained paralinguistic Conformers","date":"2022-06-24","arxiv_id":"2206.12494","repositories_listed":0,"syntology":null},{"url":null,"slug":"ahd-convnet-for-speech-emotion-classification","title":"AHD ConvNet for Speech Emotion Classification","date":"2022-06-10","arxiv_id":"2206.05286","repositories_listed":0,"syntology":null},{"url":null,"slug":"syntact-a-synthesized-database-of-basic","title":"SyntAct: A Synthesized Database of Basic Emotions","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-to-articulatory-speech-inversion-1","title":"Acoustic-to-articulatory Speech Inversion with Multi-task Learning","date":"2022-05-27","arxiv_id":"2205.13755","repositories_listed":0,"syntology":null},{"url":"/paper/emotion-recognition-in-persian-speech-using","slug":"emotion-recognition-in-persian-speech-using","title":"Emotion Recognition In Persian Speech Using Deep Neural Networks","date":"2022-04-28","arxiv_id":"2204.13601","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-speech-emotion-recognition-based-on","title":"Real-time Speech Emotion Recognition Based on Syllable-Level Feature Extraction","date":"2022-04-25","arxiv_id":"2204.11382","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-speech-emotion-recognition","title":"Probing Speech Emotion Recognition Transformers for Linguistic Knowledge","date":"2022-04-01","arxiv_id":"2204.00400","repositories_listed":0,"syntology":null},{"url":null,"slug":"cta-rnn-channel-and-temporal-wise-attention","title":"CTA-RNN: Channel and Temporal-wise Attention RNN Leveraging Pre-trained ASR Embeddings for Speech Emotion Recognition","date":"2022-03-31","arxiv_id":"2203.17023","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-architecture-search-for-speech-emotion","title":"Neural Architecture Search for Speech Emotion Recognition","date":"2022-03-31","arxiv_id":"2203.16928","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-metric-learning-for-transferable","title":"Continuous Metric Learning For Transferable Speech Emotion Recognition and Embedding Across Low-resource Languages","date":"2022-03-28","arxiv_id":"2203.14867","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-transferable-speech-emotion","title":"Towards Transferable Speech Emotion Representation: On loss functions for cross-lingual latent representations","date":"2022-03-28","arxiv_id":"2203.14865","repositories_listed":0,"syntology":null},{"url":null,"slug":"emotionnas-two-stream-architecture-search-for","title":"EmotionNAS: Two-stream Neural Architecture Search for Speech Emotion Recognition","date":"2022-03-25","arxiv_id":"2203.13617","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-federated-learning-against-adversarial","title":"Robust Federated Learning Against Adversarial Attacks for Speech Emotion Recognition","date":"2022-03-09","arxiv_id":"2203.04696","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-region-of-interest-roi","title":"Attention-based Region of Interest (ROI) Detection for Speech Emotion Recognition","date":"2022-03-03","arxiv_id":"2203.03428","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-emotion-recognition-using-self","title":"Speech Emotion Recognition using Self-Supervised Features","date":"2022-02-07","arxiv_id":"2202.03896","repositories_listed":0,"syntology":null},{"url":"/paper/speaker-normalization-for-self-supervised","slug":"speaker-normalization-for-self-supervised","title":"Speaker Normalization for Self-supervised Speech Emotion Recognition","date":"2022-02-02","arxiv_id":"2202.01252","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentiment-aware-automatic-speech-recognition","title":"Sentiment-Aware Automatic Speech Recognition pre-training for enhanced Speech Emotion Recognition","date":"2022-01-27","arxiv_id":"2201.11826","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-personalization-of-an-emotion","title":"Unsupervised Personalization of an Emotion Recognition System: The Unique Properties of the Externalization of Valence in Speech","date":"2022-01-19","arxiv_id":"2201.07876","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-on-cross-corpus-speech-emotion","title":"A study on cross-corpus speech emotion recognition and data augmentation","date":"2022-01-10","arxiv_id":"2201.03511","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-amharic-speech-emotion-dataset-and","title":"A New Amharic Speech Emotion Dataset and Classification Benchmark","date":"2022-01-07","arxiv_id":"2201.02710","repositories_listed":0,"syntology":null},{"url":null,"slug":"novel-dual-channel-long-short-term-memory","title":"Novel Dual-Channel Long Short-Term Memory Compressed Capsule Networks for Emotion Recognition","date":"2021-12-26","arxiv_id":"2112.13350","repositories_listed":0,"syntology":null},{"url":null,"slug":"classifying-emotional-utterances-by-employing","title":"Classifying Emotional Utterances by Employing Multi-modal Speech Emotion Recognition","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-through-cross-modal","title":"Representation learning through cross-modal conditional teacher-student training for speech emotion recognition","date":"2021-11-30","arxiv_id":"2112.00158","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-speech-emotion-recognition-language","title":"A Case Study on the Independence of Speech Emotion Recognition in Bangla and English Languages using Language-Independent Prosodic Features","date":"2021-11-21","arxiv_id":"2111.10776","repositories_listed":0,"syntology":null},{"url":"/paper/multimodal-emotion-recognition-on-ravdess","slug":"multimodal-emotion-recognition-on-ravdess","title":"Multimodal Emotion Recognition on RAVDESS Dataset Using Transfer Learning","date":"2021-11-18","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"biologically-inspired-speech-emotion","title":"Biologically inspired speech emotion recognition","date":"2021-11-15","arxiv_id":"2111.08112","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-emotion-recognition-using-deep-sparse","title":"Speech Emotion Recognition Using Deep Sparse Auto-Encoder Extreme Learning Machine with a New Weighting Scheme and Spectro-Temporal Features Along with Classical Feature Selection and A New Quantum-Inspired Dimension Reduction Method","date":"2021-11-13","arxiv_id":"2111.07094","repositories_listed":0,"syntology":null},{"url":"/paper/a-fine-tuned-wav2vec-2-0-hubert-benchmark-for","slug":"a-fine-tuned-wav2vec-2-0-hubert-benchmark-for","title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","date":"2021-11-04","arxiv_id":"2111.02735","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-emotion-recognition-using-quaternion","title":"Speech Emotion Recognition Using Quaternion Convolutional Neural Networks","date":"2021-10-31","arxiv_id":"2111.00404","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusing-asr-outputs-in-joint-training-for","title":"Fusing ASR Outputs in Joint Training for Speech Emotion Recognition","date":"2021-10-29","arxiv_id":"2110.15684","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-speech-emotion-recognition","title":"End-to-End Speech Emotion Recognition: Challenges of Real-Life Emergency Call Centers Data Recordings","date":"2021-10-28","arxiv_id":"2110.14957","repositories_listed":0,"syntology":null},{"url":null,"slug":"multistage-linguistic-conditioning-of","title":"Multistage linguistic conditioning of convolutional layers for speech emotion recognition","date":"2021-10-13","arxiv_id":"2110.06650","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-emotion-recognition-based-on-cnn-lstm","title":"Speech Emotion Recognition Based on CNN+LSTM Model","date":"2021-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/bigssl-exploring-the-frontier-of-large-scale","slug":"bigssl-exploring-the-frontier-of-large-scale","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","date":"2021-09-27","arxiv_id":"2109.13226","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-data-augmentation-and-deep-attention","title":"Hybrid Data Augmentation and Deep Attention-based Dilated Convolutional-Recurrent Neural Networks for Speech Emotion Recognition","date":"2021-09-18","arxiv_id":"2109.09026","repositories_listed":0,"syntology":null},{"url":null,"slug":"fser-deep-convolutional-neural-networks-for","title":"FSER: Deep Convolutional Neural Networks for Speech Emotion Recognition","date":"2021-09-15","arxiv_id":"2109.07916","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-isolated-utterances-conversational","title":"Beyond Isolated Utterances: Conversational Emotion Recognition","date":"2021-09-13","arxiv_id":"2109.06112","repositories_listed":0,"syntology":null},{"url":null,"slug":"accounting-for-variations-in-speech-emotion","title":"Accounting for Variations in Speech Emotion Recognition with Nonparametric Hierarchical Neural Network","date":"2021-09-09","arxiv_id":"2109.04316","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepemo-deep-learning-for-speech-emotion","title":"DeepEMO: Deep Learning for Speech Emotion Recognition","date":"2021-09-09","arxiv_id":"2109.04081","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-speech-emotion-recognition-using","title":"Improved Speech Emotion Recognition using Transfer Learning and Spectrogram Augmentation","date":"2021-08-05","arxiv_id":"2108.02510","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-phonetic-units-in-speech-emotion","title":"The Role of Phonetic Units in Speech Emotion Recognition","date":"2021-08-02","arxiv_id":"2108.01132","repositories_listed":0,"syntology":null},{"url":null,"slug":"expressive-voice-conversion-a-joint-framework","title":"Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer","date":"2021-07-08","arxiv_id":"2107.03748","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-analysis-of-the-emotional-content","title":"Automatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care Unit","date":"2021-06-14","arxiv_id":"2106.09539","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-attribute-aligned-strategy-for-learning","title":"An Attribute-Aligned Strategy for Learning Speech Representation","date":"2021-06-05","arxiv_id":"2106.02810","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-scattering-network-for-speech-emotion","title":"Deep scattering network for speech emotion recognition","date":"2021-05-11","arxiv_id":"2105.04806","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-interpretable-and-transferable-speech","title":"Towards Interpretable and Transferable Speech Emotion Recognition: Latent Representation Based Analysis of Features, Methods and Corpora","date":"2021-05-05","arxiv_id":"2105.02055","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-impact-of-word-error-rate-on-acoustic","title":"On the Impact of Word Error Rate on Acoustic-Linguistic Speech Emotion Recognition: An Update for the Deep Learning Era","date":"2021-04-20","arxiv_id":"2104.10121","repositories_listed":0,"syntology":null},{"url":null,"slug":"best-practices-for-noise-based-augmentation","title":"Best Practices for Noise-Based Augmentation to Improve the Performance of Deployable Speech-Based Emotion Recognition Systems","date":"2021-04-18","arxiv_id":"2104.08806","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-attentive-speech-emotion-recognition","title":"Speaker Attentive Speech Emotion Recognition","date":"2021-04-15","arxiv_id":"2104.07288","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-low-rank-representations-for","title":"Unsupervised low-rank representations for speech emotion recognition","date":"2021-04-14","arxiv_id":"2104.07072","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-emotional-text-to","title":"Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability","date":"2021-04-03","arxiv_id":"2104.01408","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-segment-based-speech-emotion","title":"Enhancing Segment-Based Speech Emotion Recognition by Deep Self-Learning","date":"2021-03-30","arxiv_id":"2103.16456","repositories_listed":0,"syntology":null},{"url":"/paper/self-paced-ensemble-learning-for-speech-and","slug":"self-paced-ensemble-learning-for-speech-and","title":"Self-paced ensemble learning for speech and audio classification","date":"2021-03-22","arxiv_id":"2103.11988","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigations-on-audiovisual-emotion","title":"Investigations on Audiovisual Emotion Recognition in Noisy Conditions","date":"2021-03-02","arxiv_id":"2103.01894","repositories_listed":0,"syntology":null},{"url":"/paper/contrastive-unsupervised-learning-for-speech","slug":"contrastive-unsupervised-learning-for-speech","title":"Contrastive Unsupervised Learning for Speech Emotion Recognition","date":"2021-02-12","arxiv_id":"2102.06357","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-linear-frequency-warping-using-constant-q","title":"Non-linear frequency warping using constant-Q transformation for speech emotion recognition","date":"2021-02-08","arxiv_id":"2102.04029","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-emotion-recognition-with-multiscale","title":"Speech Emotion Recognition with Multiscale Area Attention and Data Augmentation","date":"2021-02-03","arxiv_id":"2102.01813","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-cross-lingual-speech-emotion","title":"Unsupervised Cross-Lingual Speech Emotion Recognition Using DomainAdversarial Neural Network","date":"2020-12-21","arxiv_id":"2012.11174","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-classifier-interactive-learning-for","title":"Multi-Classifier Interactive Learning for Ambiguous Speech Emotion Recognition","date":"2020-12-10","arxiv_id":"2012.05429","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-and-recurrent-neural-networks","title":"Convolutional and Recurrent Neural Networks for Spoken Emotion Recognition","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-residual-local-feature-learning-for","title":"Deep Residual Local Feature Learning for Speech Emotion Recognition","date":"2020-11-19","arxiv_id":"2011.09767","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-use-of-self-supervised-pre-trained","title":"On the use of Self-supervised Pre-trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition","date":"2020-11-18","arxiv_id":"2011.09212","repositories_listed":0,"syntology":null},{"url":null,"slug":"recognizing-more-emotions-with-less-data","title":"Recognizing More Emotions with Less Data Using Self-supervised Transfer Learning","date":"2020-11-11","arxiv_id":"2011.05585","repositories_listed":0,"syntology":null},{"url":"/paper/context-dependent-domain-adversarial-neural","slug":"context-dependent-domain-adversarial-neural","title":"Context-Dependent Domain Adversarial Neural Network for Multimodal Emotion Recognition","date":"2020-10-28","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/empirical-interpretation-of-speech-emotion","slug":"empirical-interpretation-of-speech-emotion","title":"Empirical Interpretation of Speech Emotion Perception with Attention Based Model for Speech Emotion Recognition","date":"2020-10-28","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"copypaste-an-augmentation-method-for-speech","title":"CopyPaste: An Augmentation Method for Speech Emotion Recognition","date":"2020-10-27","arxiv_id":"2010.14602","repositories_listed":0,"syntology":null},{"url":null,"slug":"emotion-controllable-speech-synthesis-using","title":"Emotion controllable speech synthesis using emotion-unlabeled dataset with the assistance of cross-domain speech emotion recognition","date":"2020-10-26","arxiv_id":"2010.13350","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stream-attention-based-blstm-with","title":"Multi-stream Attention-based BLSTM with Feature Segmentation for Speech Emotion Recognition","date":"2020-10-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-layer-customization-for-noise-robust","title":"Dynamic Layer Customization for Noise Robust Speech Emotion Recognition in Heterogeneous Condition Training","date":"2020-10-21","arxiv_id":"2010.11226","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-window-data-augmentation-approach-for","title":"Multi-Window Data Augmentation Approach for Speech Emotion Recognition","date":"2020-10-19","arxiv_id":"2010.09895","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-speech-emotion-recognition-using","title":"Optimizing Speech Emotion Recognition using Manta-Ray Based Feature Selection","date":"2020-09-18","arxiv_id":"2009.08909","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowing-what-to-listen-to-early-attention-for","title":"Fine-grained Early Frequency Attention for Deep Speaker Representation Learning","date":"2020-09-03","arxiv_id":"2009.01822","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-transfer-learning-method-for-speech-emotion","title":"A Transfer Learning Method for Speech Emotion Recognition from Automatic Speech Recognition","date":"2020-08-06","arxiv_id":"2008.02863","repositories_listed":0,"syntology":null},{"url":"/paper/shallow-over-deep-neural-networks-a-empirical","slug":"shallow-over-deep-neural-networks-a-empirical","title":"Shallow over Deep Neural Networks: A empirical analysis for human emotion classification using audio data","date":"2020-07-03","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-transfer-learning-for-emotion","title":"Meta Transfer Learning for Emotion Recognition","date":"2020-06-23","arxiv_id":"2006.13211","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-siamese-neural-network-with-modified","title":"A Siamese Neural Network with Modified Distance Loss For Transfer Learning in Speech Emotion Recognition","date":"2020-06-04","arxiv_id":"2006.03001","repositories_listed":0,"syntology":null},{"url":null,"slug":"concealnet-an-end-to-end-neural-network-for","title":"ConcealNet: An End-to-end Neural Network for Packet Loss Concealment in Deep Speech Emotion Recognition","date":"2020-05-15","arxiv_id":"2005.07777","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-have-vxxx-bxx-connexxxn-facing-packet-loss","title":"\"I have vxxx bxx connexxxn!\": Facing Packet Loss in Deep Speech Emotion Recognition","date":"2020-05-15","arxiv_id":"2005.07757","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-cross-corpus-speech-emotion","title":"Cross Lingual Cross Corpus Speech Emotion Recognition","date":"2020-03-18","arxiv_id":"2003.07996","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-emotion-recognition-using-support","title":"Speech Emotion Recognition using Support Vector Machine","date":"2020-02-03","arxiv_id":"2002.07590","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-emotion-recognition-based-on-multi","title":"Speech Emotion Recognition Based on Multi-feature and Multi-lingual Fusion","date":"2020-01-16","arxiv_id":"2001.05908","repositories_listed":0,"syntology":null},{"url":"/paper/visually-guided-self-supervised-learning-of","slug":"visually-guided-self-supervised-learning-of","title":"Visually Guided Self Supervised Learning of Speech Representations","date":"2020-01-13","arxiv_id":"2001.04316","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-transferable-features-for-speech","title":"Learning Transferable Features for Speech Emotion Recognition","date":"2019-12-23","arxiv_id":"1912.11547","repositories_listed":0,"syntology":null},{"url":null,"slug":"bimodal-speech-emotion-recognition-using-pre","title":"Bimodal Speech Emotion Recognition Using Pre-Trained Language Models","date":"2019-11-29","arxiv_id":"1912.02610","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-invariant-affective-representation","title":"Speaker-invariant Affective Representation Learning via Adversarial Training","date":"2019-11-04","arxiv_id":"1911.01533","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-representation-learning-with-2","title":"Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition","date":"2019-10-24","arxiv_id":"1910.13806","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-emotion-recognition-via-contrastive","title":"Speech Emotion Recognition via Contrastive Loss under Siamese Networks","date":"2019-10-23","arxiv_id":"1910.11174","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-emotion-recognition-with-dual-sequence","title":"Speech Emotion Recognition with Dual-Sequence LSTM Architecture","date":"2019-10-20","arxiv_id":"1910.08874","repositories_listed":0,"syntology":null},{"url":null,"slug":"pitch-synchronous-single-frequency-filtering","title":"Pitch-Synchronous Single Frequency Filtering Spectrogram for Speech Emotion Recognition","date":"2019-08-07","arxiv_id":"1908.03054","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-discriminative-features-using-center","title":"Learning Discriminative features using Center Loss and Reconstruction as Regularizer for Speech Emotion Recognition","date":"2019-06-19","arxiv_id":"1906.08873","repositories_listed":0,"syntology":null},{"url":null,"slug":"focal-loss-based-residual-convolutional","title":"Focal Loss based Residual Convolutional Neural Network for Speech Emotion Recognition","date":"2019-06-11","arxiv_id":"1906.05682","repositories_listed":0,"syntology":null}],"record_sha256":"26cd557a684a33e59a01fe1a66f1276165dec3aa596004aae634fc8483f17e6a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}