Challenge: Pretraining a keyword Spotting model with a pretraining encoder is expensive and requires a quadratic cost.
Approach: They propose to recycle phonetic information encoded in wav2vec2.0's latent codebook, which has been typically thrown away after pretraining.
Outcome: The proposed model can be initialized with phonetic embeddings, and it delivers accuracy gains at no latency costs.

Similar Papers

wav2vec-S: Adapting Pre-trained Speech Models for Streaming (2024.findings-acl)

Copied to clipboard

Challenge: Pre-trained speech models have advanced speech-related tasks, including speech recognition and translation.
Approach: They propose a pre-trained speech model that incorporates modifications to ensure consistent speech representations during training and inference phases for streaming speech inputs.
Outcome: The proposed model outperforms baseline models on speech recognition and translation tasks and achieves a superior balance between quality and latency.
Fine-Tuning a Pre-Trained Wav2Vec2 Model for Automatic Speech Recognition- Experiments with De Zahrar Sproche (2024.lrec-main)

Copied to clipboard

Challenge: Developing semi-automatic methods of transcription and annotation based on small amounts of annotated data would free field linguists to focus on tasks that are linguistically and relationally significant during fieldwork.
Approach: They propose to use a pre-trained model to tune a generic pre-trainer model to reduce the transcription workload of field linguists.
Outcome: The proposed system reduces the transcription workload of field linguists by averaging a pre-trained model with a language-specific tuning.
Fine-grained Artificial Neurons in Audio-transformers for Disentangling Neural Auditory Encoding (2023.findings-acl)

Copied to clipboard

Challenge: Existing studies treat each transformer encoding layer as a single artificial neuron . layer-level embeddings aggregate multiple types of contextual attention captured by multiple head modules .
Approach: They propose to embed each transformer encoding layer as a single artificial neuron . they propose to couple those ANs with their biological-neuron counterparts in the human brain .
Outcome: The proposed models can be used to link representations to brain activity, the authors say . their results show that the proposed models carry meaningful neurolinguistic information .
Self-supervised Rewiring of Pre-trained Speech Encoders: Towards Faster Fine-tuning with Less Labels in Speech Processing (2022.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained speech encoders have facilitated great success across various speech processing tasks, but fine-tuning them for downstream tasks requires large training data to converge or to achieve state-of-the-art.
Approach: They propose to rewire pre-trained speech encoders to improve their representation space without task-specific labels by neutrally synthesising audio inputs and frame masking.
Outcome: The proposed model shows consistent improvement in isotropy in the representation space on 6 speech processing tasks.
Language-Codec: Bridging Discrete Codec Representations and Speech Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing gaps between discrete acoustic codecs and downstream speech language models . initial channel of codebooks contains excessive information, making it difficult to generate tokens from weakly supervised signals such as text.
Approach: They propose a discrete acoustic codec for generating acustic tokens from weakly supervised signals.
Outcome: The proposed language-codec outperforms competing audio compression algorithms and validates on downstream speech language models.
RedApt: An Adaptor for wav2vec 2 EncodingFaster and Smaller Speech Translation without Quality Compromise (2022.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained speech Transformers in speech translation systems have facilitated state-of-the-art (SotA) results, but their computational cost is high.
Approach: They propose a Reducer Adaptor block that could be seamlessly integrated within any Transformer-based speech encoding architecture.
Outcome: The proposed Reducer Adaptor block outperforms the existing SotA architecture by an average of 0.68 BLEU score on 8 language pairs from Must-C.
Transformer-based Speech Model Learns Well as Infants and Encodes Abstractions through Exemplars in the Poverty of the Stimulus Environment (2025.coling-main)

Copied to clipboard

Challenge: Existing theories of language learning for infants are inadequate, according to Chomsky . infants learn language in impoverished environments, according a new study .
Approach: They designed a series of tasks, scenarios, and metrics to simulate the POS . they found that the emerging speech model wav2vec2.0 can learn well in noisy Mandarin environments.
Outcome: The proposed model can learn in noisy and sparse Mandarin environments.
Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia (2020.emnlp-demos)

Copied to clipboard

Challenge: Existing tools for learning the embeddings of words and entities from Wikipedia are not yet available.
Approach: They propose a Python-based tool for learning Wikipedia embeddings from Wikipedia . they use a Wikipedia dump file as an argument to issue a single command .
Outcome: The proposed tool achieves state-of-the-art results on the KORE entity relatedness dataset and competitive results on benchmark datasets.
Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings (2022.acl-long)

Copied to clipboard

Challenge: Contextualized embeddings are expensive and resource-demanding, hence environmentally unfriendly.
Approach: They propose a method to convert contextualized embeddings from pre-trained models into static embeddables using synonym knowledge and weighted vector distribution.
Outcome: The proposed method outperforms baseline embeddings by a large margin through extrinsic and intrinsic tasks.
Wav2Prompt: End-to-End Speech Prompt Learning and Task-based Fine-tuning for Text-based LLMs (2025.naacl-long)

Copied to clipboard

Challenge: Text-based large language models (LLMs) can be applied to a wide range of tasks without being explicitly trained.
Approach: They propose a method which integrates spoken input with a text-based large language model (LLM) it takes LLM token embeddings as training targets and utilises a continuous integrate-and-fire mechanism for explicit speech-text alignment.
Outcome: The proposed model can be applied to speech translation, speech understanding and spoken-query-based question answering tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations