Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024

• URL: http://arxiv.org/abs/2406.16777v1
• Date: Mon, 24 Jun 2024 16:38:17 GMT
• Title: Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024
• Authors: Sai Koneru, Thai-Binh Nguyen, Ngoc-Quan Pham, Danni Liu, Zhaolin Li, Alexander Waibel, Jan Niehues,
• Abstract summary: Large Language Models (LLMs) are currently under exploration for various tasks, including Automatic Speech Recognition (ASR), Machine Translation (MT), and even End-to-End Speech Translation (ST)
• Score: 61.189875635090225
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are currently under exploration for various tasks, including Automatic Speech Recognition (ASR), Machine Translation (MT), and even End-to-End Speech Translation (ST). In this paper, we present KIT's offline submission in the constrained + LLM track by incorporating recently proposed techniques that can be added to any cascaded speech translation. Specifically, we integrate Mistral-7B\footnote{mistralai/Mistral-7B-Instruct-v0.1} into our system to enhance it in two ways. Firstly, we refine the ASR outputs by utilizing the N-best lists generated by our system and fine-tuning the LLM to predict the transcript accurately. Secondly, we refine the MT outputs at the document level by fine-tuning the LLM, leveraging both ASR and MT predictions to improve translation quality. We find that integrating the LLM into the ASR and MT systems results in an absolute improvement of $0.3\%$ in Word Error Rate and $0.65\%$ in COMET for tst2019 test set. In challenging test sets with overlapping speakers and background noise, we find that integrating LLM is not beneficial due to poor ASR performance. Here, we use ASR with chunked long-form decoding to improve context usage that may be unavailable when transcribing with Voice Activity Detection segmentation alone.

Related papers

• Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs [20.97172337899685]
  We propose pre-training large language models (LLMs) on Pinyin embedding sequences to generate corresponding Chinese characters. This step enables the LLM to adapt to generating text from pronunciation features before encountering real speech data. In AISHELL-1 corpus, our approach yields a 9.5% relative improvement in ASR tasks compared to the baseline.
  arXiv  Detail & Related papers  (2024-09-24T12:06:31Z)
• TasTe: Teaching Large Language Models to Translate through Self-Reflection [82.83958470745381]
  Large language models (LLMs) have exhibited remarkable performance in various natural language processing tasks. We propose the TasTe framework, which stands for translating through self-reflection. The evaluation results in four language directions on the WMT22 benchmark reveal the effectiveness of our approach compared to existing methods.
  arXiv  Detail & Related papers  (2024-06-12T17:21:21Z)
• Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning [57.323716555996114]
  Off-target translation remains an unsolved problem, especially for low-resource languages. Recent works have either designed advanced prompting strategies to highlight the functionality of translation instructions or exploited the in-context learning ability of LLMs. In this work, we design a two-stage fine-tuning algorithm to improve the instruction-following ability (especially the translation direction) of LLMs.
  arXiv  Detail & Related papers  (2024-03-21T13:47:40Z)
• Speech Translation with Large Language Models: An Industrial Practice [64.5419534101104]
  We introduce LLM-ST, a novel and effective speech translation model constructed upon a pre-trained large language model (LLM) By integrating the large language model (LLM) with a speech encoder and employing multi-task instruction tuning, LLM-ST can produce accurate timestamped transcriptions and translations. Through rigorous experimentation on English and Chinese datasets, we showcase the exceptional performance of LLM-ST.
  arXiv  Detail & Related papers  (2023-12-21T05:32:49Z)
• Exploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Study [0.0]
  This paper explores the integration of Large Language Models (LLMs) into Automatic Speech Recognition (ASR) systems. Our primary focus is to investigate the potential of using an LLM's in-context learning capabilities to enhance the performance of ASR systems.
  arXiv  Detail & Related papers  (2023-07-13T02:31:55Z)
• Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis [103.89753784762445]
  Large language models (LLMs) have demonstrated remarkable potential in handling multilingual machine translation (MMT) This paper systematically investigates the advantages and challenges of LLMs for MMT. We thoroughly evaluate eight popular LLMs, including ChatGPT and GPT-4.
  arXiv  Detail & Related papers  (2023-04-10T15:51:30Z)
• On Language Model Integration for RNN Transducer based Speech Recognition [49.84285563767935]
  We study various ILM correction-based LM integration methods formulated in a common RNN-T framework. We provide a decoding interpretation on two major reasons for performance improvement with ILM correction. We also propose an exact-ILM training framework by extending the proof given in the hybrid autoregressive transducer.
  arXiv  Detail & Related papers  (2021-10-13T16:30:46Z)
• Cross-Utterance Language Models with Acoustic Error Sampling [1.376408511310322]
  Cross-utterance LM (CULM) is proposed to augment the input to a standard long short-term memory (LSTM) LM. An acoustic error sampling technique is proposed to reduce the mismatch between training and test-time. Experiments performed on both AMI and Switchboard datasets show that CULMs outperform the LSTM LM baseline WER.
  arXiv  Detail & Related papers  (2020-08-19T17:40:11Z)
• Jointly Trained Transformers models for Spoken Language Translation [2.3886615435250302]
  This work trains SLT systems with ASR objective as an auxiliary loss and both the networks are connected through neural hidden representations. This architecture has improved from BLEU from 36.8 to 44.5. All the experiments are reported on English-Portuguese speech translation task using How2 corpus.
  arXiv  Detail & Related papers  (2020-04-25T11:28:39Z)

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.