Methods › General › Attention Modules › SimAdapter
SimAdapter
Introduced by Wenxin Hou et al. in Exploiting Adapters for Cross-lingual Low-resource Speech Recognition
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SimAdapter is a module for explicitly learning knowledge from adapters. SimAdapter aims to learn the similarities between the source and target languages during fine-tuning using the adapters, and the similarity is based on an attention mechanism.
The detailed composition of the SimAdapter is shown in the Figure. By taking the language-agnostic representations from the backbone model as the query, and the language-specific outputs from multiple adapter as the keys and values, the final output for SimAdapter over attention are computed as (For notation simplicity, we omit the layer index l below):
SimAdapter(z, a_(S₁, S₂, …, S_N))=∑ᵢ₌₁ᴺ Attn(z, a_(Sᵢ)) ·(a_(Sᵢ) W_V)
where SimAdapter (·) and Attn(·) denotes the SimAdapter and attention operations, respectively. Specifically, the attention operation is computed as:
Attn(z, a)=Softmax(((z W_Q)(a W_K)^⊤)/τ)
where τ is the temperature coefficient, W_Q, W_K, W_V are attention matrices. Note that while W_Q, W_K are initialized randomly, W_V is initialized with a diagonal of ones and the rest of the matrix with small weights (1 e-6) to retain the adapter representations. Furthermore, a regularization term is introduced to avoid drastic feature changes:
ℒ_(reg)=∑_(i, j)((I_V)_(i, j)-(W_V)_(i, j))²
where I_V is the identity matrix with the same size as W_V
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 1 · with a code link: 1 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran: none of the 1 tagged papers has a Syntology run on record
Page 1 of 1: paper 1 of 1, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Exploiting Adapters for Cross-lingual Low-resource Speech Recognition 18 May 2021 · 2 repositories · arXiv:2105.11905
Tasks archive 2025-07-28
5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Cross-Lingual ASR | 1 |
| General Knowledge | 1 |
| Meta-Learning | 1 |
| Speech Recognition | 1 |
| speech-recognition | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections