paper-with-me

Papers

Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation

2024-02-08 · Heeseung Kim, Soonshin Seo, Kyeongseok Jeong, Ohsung Kwon, Soyoon Kim, Jungwhan Kim, Jaehong Lee, Eunwoo Song, Myungwoo Oh, Jung-Woo Ha, Sungroh Yoon, Kang Min Yoo

Recent work shows promising results in expanding the capabilities of large language models (LLM) to directly understand and synthesize speech. However, an LLM-based strategy for modeling spoken dialogs remains elusive, calling for further investigation. This paper introduces an extensive speech-text LLM framework, the Unified Spoken Dialog Model (USDM), designed to generate coherent spoken responses with naturally occurring prosodic features relevant to the given input speech without relying on explicit automatic speech recognition (ASR) or text-to-speech (TTS) systems. We have verified the inclusion of prosody in speech tokens that predominantly contain semantic information and have used this foundation to construct a prosody-infused speech-text model. Additionally, we propose a generalized speech-text pretraining scheme that enhances the capture of cross-modal semantics. To construct USDM, we fine-tune our speech-text model on spoken dialog data using a multi-step spoken dialog template that stimulates the chain-of-reasoning capabilities exhibited by the underlying LLM. Automatic and human evaluations on the DailyTalk dataset demonstrate that our approach effectively generates natural-sounding spoken responses, surpassing previous and cascaded baselines. Our code and checkpoints are available at https://github.com/naver-ai/usdm.

📄 PDF Abstract BibTeX arXiv:2402.05706

Code (1)

naver-ai/usdm 공식 구현 pytorch

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognitiontext-to-speechText to Speech

Similar Papers 제목 키워드 기반

Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning

2026-03-16 · Jingxiang Chen, Minseok Kim, Seong-Gyun Leem, Yin Huang 외 arxiv

Speech large language models (LLMs) observe paralinguistic cues such as prosody, emotion, and non-verbal sounds--crucial for intent understanding. However, leveraging these cues faces challenges: limited training data, a…

Reinforcement LearningResponse Generation

Deep Neural Baselines for Computational Paralinguistics

2019-07-05 · Daniel Elsner, Stefan Langer, Fabian Ritz, Robert Müller 외

Detecting sleepiness from spoken language is an ambitious task, which is addressed by the Interspeech 2019 Computational Paralinguistics Challenge (ComParE). We propose an end-to-end deep learning approach to detect and …

Audio ClassificationBIG-bench Machine LearningFeature Engineering

A Survey on Paralinguistics in Tamil Speech Processing

2021-04-01 · EACL (DravidianLangTech) 2021 4 · Anosha Ignatius, Uthayasanker Thayasivam

Speech carries not only the semantic content but also the paralinguistic information which captures the speaking style. Speaker traits and emotional states affect how words are being spoken. The research on paralinguisti…

Emotion RecognitionSpeaker Identificationspeech-recognitionSpeech Recognition+1

The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates

2021-02-24 · Björn W. Schuller, Anton Batliner, Christian Bergler, Cecilia Mascolo 외

The INTERSPEECH 2021 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the COVID-19 Cough and COVID-19 Speech Sub-Cha…

Binary ClassificationRepresentation Learning

Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue

2023-12-23 · Guan-Ting Lin, Prashanth Gurunath Shivakumar, Ankur Gandhe, Chao-Han Huck Yang 외

Large Language Models (LLMs) have demonstrated superior abilities in tasks such as chatting, reasoning, and question-answering. However, standard LLMs may ignore crucial paralinguistic information, such as sentiment, emo…

AttributeLanguage ModelingLanguage ModellingQuestion Answering+3