Investigating the Effects of Large-Scale Pseudo-Stereo Data and Different Speech Foundation Model on Dialogue Generative Spoken Language Model

• URL: http://arxiv.org/abs/2407.01911v1
• Date: Tue, 2 Jul 2024 03:22:41 GMT
• Title: Investigating the Effects of Large-Scale Pseudo-Stereo Data and Different Speech Foundation Model on Dialogue Generative Spoken Language Model
• Authors: Yu-Kuan Fu, Cheng-Kuang Lee, Hsiu-Hsuan Wang, Hung-yi Lee,
• Abstract summary: We develop a pipeline capable of transforming single-channel dialogue data into pseudo-stereo data. This expanded our training dataset from a mere 2,000 to an impressive 17,600 hours. The inclusion of this pseudo-stereo data has proven to be effective in improving the performance of spoken dialogue language models.
• Score: 47.67067056593085
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent efforts in Spoken Dialogue Modeling aim to synthesize spoken dialogue without the need for direct transcription, thereby preserving the wealth of non-textual information inherent in speech. However, this approach faces a challenge when speakers talk simultaneously, requiring stereo dialogue data with speakers recorded on separate channels, a notably scarce resource. To address this, we have developed an innovative pipeline capable of transforming single-channel dialogue data into pseudo-stereo data. This expanded our training dataset from a mere 2,000 to an impressive 17,600 hours, significantly enriching the diversity and quality of the training examples available. The inclusion of this pseudo-stereo data has proven to be effective in improving the performance of spoken dialogue language models. Additionally, we explored the use of discrete units of different speech foundation models for spoken dialogue generation.

Related papers

• J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling [43.87842102048749]
  Spoken dialogue plays a crucial role in human-AI interactions, necessitating dialogue-oriented spoken language models (SLMs) To ensure hiqh-quality speech generation, the data must be spontaneous like in-wild data and must be acoustically clean with noise removed. This study addresses this gap by constructing and releasing a large-scale spoken dialogue corpus, named Japanese Corpus for Human-AI Talks (J-CHAT) This paper presents a language-independent method for corpus construction and describes experiments on dialogue generation using SLMs trained on J-CHAT.
  arXiv  Detail & Related papers  (2024-07-22T17:46:50Z)
• SPECTRUM: Speaker-Enhanced Pre-Training for Long Dialogue Summarization [48.284512017469524]
  Multi-turn dialogues are characterized by their extended length and the presence of turn-taking conversations. Traditional language models often overlook the distinct features of these dialogues by treating them as regular text. We propose a speaker-enhanced pre-training method for long dialogue summarization.
  arXiv  Detail & Related papers  (2024-01-31T04:50:00Z)
• Pre-training Multi-party Dialogue Models with Latent Discourse Inference [85.9683181507206]
  We pre-train a model that understands the discourse structure of multi-party dialogues, namely, to whom each utterance is replying. To fully utilize the unlabeled data, we propose to treat the discourse structures as latent variables, then jointly infer them and pre-train the discourse-aware model.
  arXiv  Detail & Related papers  (2023-05-24T14:06:27Z)
• SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents [72.42049370297849]
  SpokenWOZ is a large-scale speech-text dataset for spoken TOD. Cross-turn slot and reasoning slot detection are new challenges for SpokenWOZ.
  arXiv  Detail & Related papers  (2023-05-22T13:47:51Z)
• "How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations [87.95711406978157]
  This work presents a new benchmark on spoken task-oriented conversations. We study multi-domain dialogue state tracking and knowledge-grounded dialogue modeling. Our data set enables speech-based benchmarking of task-oriented dialogue systems.
  arXiv  Detail & Related papers  (2021-09-28T04:51:04Z)
• Low-resource expressive text-to-speech using data augmentation [12.396086122947679]
  We present a novel 3-step methodology to circumvent the costly operation of recording large amounts of target data. We augment data via voice conversion by leveraging recordings in the desired speaking style from other speakers. Next, we use that synthetic data on top of the available recordings to train a TTS model.
  arXiv  Detail & Related papers  (2020-11-11T11:22:37Z)
• Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue [76.88174667929665]
  A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. In the existing retrieval-based multi-turn dialogue modeling, the pre-trained language models (PrLMs) as encoder represent the dialogues coarsely. We propose a novel model to fill such a gap by modeling the effective utterance-aware and speaker-aware representations entailed in a dialogue history.
  arXiv  Detail & Related papers  (2020-09-14T15:07:19Z)
• Interview: A Large-Scale Open-Source Corpus of Media Dialog [11.28504775964698]
  We introduce 'Interview': a large-scale (105K conversations) media dialog dataset collected from news interview transcripts. Compared to existing large-scale proxies for conversational data, language models trained on our dataset exhibit better zero-shot out-of-domain performance. 'Interview' contains speaker role annotations for each turn, facilitating the development of engaging, responsive dialog systems.
  arXiv  Detail & Related papers  (2020-04-07T02:44:50Z)

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.