A Comprehensive Solution to Connect Speech Encoder and Large Language Model for ASR

• URL: http://arxiv.org/abs/2406.17272v1
• Date: Tue, 25 Jun 2024 04:35:50 GMT
• Title: A Comprehensive Solution to Connect Speech Encoder and Large Language Model for ASR
• Authors: Van Tung Pham, Yist Lin, Tao Han, Wei Li, Jun Zhang, Lu Lu, Yuxuan Wang,
• Abstract summary: Recent works have shown promising results in connecting speech encoders to large language models (LLMs) for speech recognition. However, several limitations persist, including limited fine-tuning options, a lack of mechanisms to enforce speech-text alignment, and high insertion errors. This paper presents a comprehensive solution to address these issues.
• Score: 14.380210167130032
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent works have shown promising results in connecting speech encoders to large language models (LLMs) for speech recognition. However, several limitations persist, including limited fine-tuning options, a lack of mechanisms to enforce speech-text alignment, and high insertion errors especially in domain mismatch conditions. This paper presents a comprehensive solution to address these issues. We begin by investigating more thoughtful fine-tuning schemes. Next, we propose a matching loss to enhance alignment between modalities. Finally, we explore training and inference methods to mitigate high insertion errors. Experimental results on the Librispeech corpus demonstrate that partially fine-tuning the encoder and LLM using parameter-efficient methods, such as LoRA, is the most cost-effective approach. Additionally, the matching loss improves modality alignment, enhancing performance. The proposed training and inference methods significantly reduce insertion errors.

Related papers

• PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding [44.77985942208969]
  PRoDeliberation is a novel method leveraging a Connectionist Temporal Classification-based decoding strategy as well as a denoising objective to train robust non-autoregressive deliberation models. We show that PRoDeliberation achieves the latency reduction of parallel decoding (2-10x improvement over autoregressive models) while retaining the ability to correct Automatic Speech Recognition (ASR) mistranscriptions.
  arXiv  Detail & Related papers  (2024-06-12T02:46:17Z)
• An Analysis of BPE Vocabulary Trimming in Neural Machine Translation [56.383793805299234]
  vocabulary trimming is a postprocessing step that replaces rare subwords with their component subwords. We show that vocabulary trimming fails to improve performance and is even prone to incurring heavy degradation.
  arXiv  Detail & Related papers  (2024-03-30T15:29:49Z)
• Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars [11.279507894576213]
  This paper contributes an incremental synthesis that allows early rejection of syntactically incorrect code. We extend the Earley parsing algorithm to allow for left and right quotients of context-free grammars.
  arXiv  Detail & Related papers  (2024-02-28T02:12:47Z)
• Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding [46.485363806259265]
  Speculative Decoding has emerged as a novel decoding paradigm for Large Language Models (LLMs) inference. In each decoding step, this method first drafts several future tokens efficiently and then verifies them in parallel. This paper presents a comprehensive overview and analysis of this promising decoding paradigm.
  arXiv  Detail & Related papers  (2024-01-15T17:26:50Z)
• Understanding and Mitigating Classification Errors Through Interpretable Token Patterns [58.91023283103762]
  Characterizing errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors. We propose to discover those patterns of tokens that distinguish correct and erroneous predictions. We show that our method, Premise, performs well in practice.
  arXiv  Detail & Related papers  (2023-11-18T00:24:26Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• Improving Joint Speech-Text Representations Without Alignment [92.60384956736536]
  We show that joint speech-text encoders naturally achieve consistent representations across modalities by disregarding sequence length. We argue that consistency losses could forgive length differences and simply assume the best alignment.
  arXiv  Detail & Related papers  (2023-08-11T13:28:48Z)
• Weakly-supervised forced alignment of disfluent speech using phoneme-level modeling [10.283092375534311]
  We propose a simple and effective modification of alignment graph construction using weighted Finite State Transducers. The proposed weakly-supervised approach alleviates the need for verbatim transcription of speech disfluencies for forced alignment. Our evaluation on a corrupted version of the TIMIT test set and the UCLASS dataset shows significant improvements.
  arXiv  Detail & Related papers  (2023-05-30T09:57:36Z)
• AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translation [36.12146100483228]
  AdaTranS adapts the speech features with a new shrinking mechanism to mitigate the length mismatch between speech and text features. Experiments on the MUST-C dataset demonstrate that AdaTranS achieves better performance than the other shrinking-based methods.
  arXiv  Detail & Related papers  (2022-12-17T16:14:30Z)
• Single-channel speech separation using Soft-minimum Permutation Invariant Training [60.99112031408449]
  A long-lasting problem in supervised speech separation is finding the correct label for each separated speech signal. Permutation Invariant Training (PIT) has been shown to be a promising solution in handling the label ambiguity problem. In this work, we propose a probabilistic optimization framework to address the inefficiency of PIT in finding the best output-label assignment.
  arXiv  Detail & Related papers  (2021-11-16T17:25:05Z)
• Joint Contextual Modeling for ASR Correction and Language Understanding [60.230013453699975]
  We propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with language understanding (LU) We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.
  arXiv  Detail & Related papers  (2020-01-28T22:09:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.