paper-with-me

Papers

Generative Spoken Dialogue Language Modeling

2022-03-30 · Tu Anh Nguyen, Eugene Kharitonov, Jade Copet, Yossi Adi, Wei-Ning Hsu, Ali Elkahky, Paden Tomasello, Robin Algayres, Benoit Sagot, Abdelrahman Mohamed, Emmanuel Dupoux

We introduce dGSLM, the first "textless" model able to generate audio samples of naturalistic spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with a dual-tower transformer architecture with cross-attention trained on 2000 hours of two-channel raw conversational audio (Fisher dataset) without any text or labels. We show that our model is able to generate speech, laughter and other paralinguistic signals in the two channels simultaneously and reproduces more naturalistic and fluid turn-taking compared to a text-based cascaded model.

📄 PDF Abstract BibTeX arXiv:2203.16502

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

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

2024-07-02 · Yu-Kuan Fu, Cheng-Kuang Lee, Hsiu-Hsuan Wang, Hung-Yi Lee

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 …

Dialogue GenerationDiversityLanguage ModelingLanguage Modelling

Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations

2022-03-08 · Ruijie Yan, Shuang Peng, Haitao Mi, Liang Jiang 외

Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data. This paper presents our approach to build generalized models for the Knowled…

Data Augmentationdomain classificationMulti-Task Learning

NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction

2025-06-01 · Qichao Wang, Ziqiao Meng, Wenqian Cui, Yifei Zhang 외

Inspired by the impressive capabilities of GPT-4o, there is growing interest in enabling speech language models (SLMs) to engage in natural, fluid spoken interactions with humans. Recent advancements have led to the deve…

DecoderLanguage ModelingLanguage Modelling

J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling

2024-07-22 · Wataru Nakata, Kentaro Seki, Hitomi Yanaka, Yuki Saito 외

Spoken dialogue plays a crucial role in human-AI interactions, necessitating dialogue-oriented spoken language models (SLMs). To develop versatile SLMs, large-scale and diverse speech datasets are essential. Additionally…

Dialogue GenerationLanguage ModelingLanguage Modelling

Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities

2025-03-06 · Guan-Ting Lin, Jiachen Lian, Tingle Li, Qirui Wang 외

Spoken dialogue modeling poses challenges beyond text-based language modeling, requiring real-time interaction, turn-taking, and backchanneling. While most Spoken Dialogue Models (SDMs) operate in half-duplex mode-proces…

Language ModelingLanguage ModellingManagement