SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models

• URL: http://arxiv.org/abs/2501.08421v1
• Date: Tue, 14 Jan 2025 20:24:12 GMT
• Title: SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models
• Authors: Anurag Kumar, Rohit Paturi, Amber Afshan, Sundararajan Srinivasan,
• Abstract summary: We introduce a novel acoustic conditioning approach to provide more fine-grained information from the acoustic diarizer to the LLM. Our approach significantly reduces the speaker error rates by 24-43% across Fisher, Callhome, and RT03-CTS datasets.
• Score: 15.098665255729507
• License:
• Abstract: Speaker Diarization (SD) is a crucial component of modern end-to-end ASR pipelines. Traditional SD systems, which are typically audio-based and operate independently of ASR, often introduce speaker errors, particularly during speaker transitions and overlapping speech. Recently, language models including fine-tuned large language models (LLMs) have shown to be effective as a second-pass speaker error corrector by leveraging lexical context in the transcribed output. In this work, we introduce a novel acoustic conditioning approach to provide more fine-grained information from the acoustic diarizer to the LLM. We also show that a simpler constrained decoding strategy reduces LLM hallucinations, while avoiding complicated post-processing. Our approach significantly reduces the speaker error rates by 24-43% across Fisher, Callhome, and RT03-CTS datasets, compared to the first-pass Acoustic SD.

Related papers

• MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models [59.80042864360884]
  Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately. This paper introduces a novel approach, leveraging a frozen multilingual ASR model to incorporate speaker attribution into the transcriptions.
  arXiv  Detail & Related papers  (2024-11-27T09:01:08Z)
• AG-LSEC: Audio Grounded Lexical Speaker Error Correction [9.54540722574194]
  Speaker Diarization (SD) systems are typically audio-based and operate independently of the ASR system in traditional speech transcription pipelines. We propose to enhance and acoustically ground the Lexical Speaker Error Correction (LSEC) system with speaker scores directly derived from the existing SD pipeline. This approach achieves significant relative WDER reductions in the range of 25-40% over the audio-based SD, ASR system and beats the LSEC system by 15-25% relative on RT03-CTS, Callhome American English and Fisher datasets.
  arXiv  Detail & Related papers  (2024-06-25T04:20:49Z)
• Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correction [4.409889336732851]
  Speaker diarization (SD) is typically used with an automatic speech recognition (ASR) system to ascribe speaker labels to recognized words. This approach can lead to speaker errors especially around speaker turns and regions of speaker overlap. We propose a novel second-pass speaker error correction system using lexical information.
  arXiv  Detail & Related papers  (2023-06-15T17:47:41Z)
• BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR [54.23941663326509]
  Frequent speaker changes can make speaker change prediction difficult. We propose boundary-aware serialized output training (BA-SOT) Compared to original SOT, BA-SOT reduces CER/UD-CER by 5.1%/14.0%.
  arXiv  Detail & Related papers  (2023-05-23T06:08:13Z)
• Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings [53.11450530896623]
  This paper presents a streaming speaker-attributed automatic speech recognition (SA-ASR) model that can recognize "who spoke what" Our model is based on token-level serialized output training (t-SOT) which was recently proposed to transcribe multi-talker speech in a streaming fashion. The proposed model achieves substantially better accuracy than a prior streaming model and shows comparable or sometimes even superior results to the state-of-the-art offline SA-ASR model.
  arXiv  Detail & Related papers  (2022-03-30T21:42:00Z)
• ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion [49.617722668505834]
  We show that our approach permits the application of speech synthesis and voice conversion to improve ASR systems using only one target-language speaker during model training. It is possible to obtain promising ASR training results with our data augmentation method using only a single real speaker in a target language.
  arXiv  Detail & Related papers  (2022-03-29T11:55:30Z)
• Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech [62.95422526044178]
  We use Model Agnostic Meta-Learning (MAML) as the training algorithm of a multi-speaker TTS model. We show that Meta-TTS can synthesize high speaker-similarity speech from few enrollment samples with fewer adaptation steps than the speaker adaptation baseline.
  arXiv  Detail & Related papers  (2021-11-07T09:53:31Z)
• Segmenting Subtitles for Correcting ASR Segmentation Errors [11.854481771567503]
  We propose a model for correcting the acoustic segmentation of ASR models for low-resource languages. We train a neural tagging model for correcting ASR acoustic segmentation and show that it improves downstream performance.
  arXiv  Detail & Related papers  (2021-04-16T03:04:10Z)
• End-to-End Speaker-Attributed ASR with Transformer [41.7739129773237]
  This paper presents an end-to-end speaker-attributed automatic speech recognition system. It jointly performs speaker counting, speech recognition and speaker identification for monaural multi-talker audio.
  arXiv  Detail & Related papers  (2021-04-05T19:54:15Z)
• Audio-visual Multi-channel Recognition of Overlapped Speech [79.21950701506732]
  This paper presents an audio-visual multi-channel overlapped speech recognition system featuring tightly integrated separation front-end and recognition back-end. Experiments suggest that the proposed multi-channel AVSR system outperforms the baseline audio-only ASR system by up to 6.81% (26.83% relative) and 22.22% (56.87% relative) absolute word error rate (WER) reduction on overlapped speech constructed using either simulation or replaying of the lipreading sentence 2 dataset respectively.
  arXiv  Detail & Related papers  (2020-05-18T10:31:19Z)
• End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification [45.38809571153867]
  We propose the End-to-End Neural Diarization (EEND) in which a neural network directly outputs speaker diarization results. By feeding multi-speaker recordings with corresponding speaker segment labels, our model can be easily adapted to real conversations.
  arXiv  Detail & Related papers  (2020-02-24T14:53:32Z)

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.