M2-CTTS: End-to-End Multi-scale Multi-modal Conversational
Text-to-Speech Synthesis
- URL: http://arxiv.org/abs/2305.02269v1
- Date: Wed, 3 May 2023 16:59:38 GMT
- Title: M2-CTTS: End-to-End Multi-scale Multi-modal Conversational
Text-to-Speech Synthesis
- Authors: Jinlong Xue, Yayue Deng, Fengping Wang, Ya Li, Yingming Gao, Jianhua
Tao, Jianqing Sun, Jiaen Liang
- Abstract summary: M2-CTTS aims to comprehensively utilize historical conversation and enhance prosodic expression.
We design a textual context module and an acoustic context module with both coarse-grained and fine-grained modeling.
- Score: 38.85861825252267
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Conversational text-to-speech (TTS) aims to synthesize speech with proper
prosody of reply based on the historical conversation. However, it is still a
challenge to comprehensively model the conversation, and a majority of
conversational TTS systems only focus on extracting global information and omit
local prosody features, which contain important fine-grained information like
keywords and emphasis. Moreover, it is insufficient to only consider the
textual features, and acoustic features also contain various prosody
information. Hence, we propose M2-CTTS, an end-to-end multi-scale multi-modal
conversational text-to-speech system, aiming to comprehensively utilize
historical conversation and enhance prosodic expression. More specifically, we
design a textual context module and an acoustic context module with both
coarse-grained and fine-grained modeling. Experimental results demonstrate that
our model mixed with fine-grained context information and additionally
considering acoustic features achieves better prosody performance and
naturalness in CMOS tests.
Related papers
- OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation [24.68804661538364]
Full spoken dialogue systems significantly mirror human-human interactions.
achieving low latency and natural interactions is a significant challenge.
End-to-end full-to-end spoken dialogue systems are a promising direction for developing efficient and natural end-to-end systems.
Audio samples of dialogues generated by OmniFlatten can be found at this web site.
arXiv Detail & Related papers (2024-10-23T11:58:58Z) - VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning [64.56272011710735]
We propose a novel single-stage joint speech-text SFT approach on the low-rank adaptation (LoRA) of the large language models (LLMs) backbone.
Compared to previous SpeechLMs with 7B or 13B parameters, our 3B model demonstrates superior performance across various speech benchmarks.
arXiv Detail & Related papers (2024-10-23T00:36:06Z) - Emphasis Rendering for Conversational Text-to-Speech with Multi-modal Multi-scale Context Modeling [40.32021786228235]
Conversational Text-to-Speech (CTTS) aims to accurately express an utterance with the appropriate style within a conversational setting.
We propose a novel Emphasis Rendering scheme for the CTTS model, termed ER-CTTS.
To address data scarcity, we create emphasis intensity annotations on the existing conversational dataset (DailyTalk)
arXiv Detail & Related papers (2024-10-12T13:02:31Z) - MM-TTS: A Unified Framework for Multimodal, Prompt-Induced Emotional Text-to-Speech Synthesis [70.06396781553191]
Multimodal Emotional Text-to-Speech System (MM-TTS) is a unified framework that leverages emotional cues from multiple modalities to generate highly expressive and emotionally resonant speech.
MM-TTS consists of two key components: the Emotion Prompt Alignment Module (EP-Align), which employs contrastive learning to align emotional features across text, audio, and visual modalities, and the Emotion Embedding-Induced TTS (EMI-TTS), which integrates the aligned emotional embeddings with state-of-the-art TTS models to synthesize speech that accurately reflects the intended emotions.
arXiv Detail & Related papers (2024-04-29T03:19:39Z) - Integrating Paralinguistics in Speech-Empowered Large Language Models for Natural Conversation [46.93969003104427]
This paper introduces an extensive speech-text LLM framework, the Unified Spoken Dialog Model (USDM)
USDM is designed to generate coherent spoken responses with naturally occurring prosodic features relevant to the given input speech.
Our approach effectively generates natural-sounding spoken responses, surpassing previous and cascaded baselines.
arXiv Detail & Related papers (2024-02-08T14:35:09Z) - Towards Joint Modeling of Dialogue Response and Speech Synthesis based
on Large Language Model [8.180382743037082]
This paper explores the potential of constructing an AI spoken dialogue system that "thinks how to respond" and "thinks how to speak" simultaneously.
arXiv Detail & Related papers (2023-09-20T01:48:27Z) - Visual-Aware Text-to-Speech [101.89332968344102]
We present a new visual-aware text-to-speech (VA-TTS) task to synthesize speech conditioned on both textual inputs and visual feedback of the listener in face-to-face communication.
We devise a baseline model to fuse phoneme linguistic information and listener visual signals for speech synthesis.
arXiv Detail & Related papers (2023-06-21T05:11:39Z) - Spoken Style Learning with Multi-modal Hierarchical Context Encoding for
Conversational Text-to-Speech Synthesis [59.27994987902646]
The study about learning spoken styles from historical conversations is still in its infancy.
Only the transcripts of the historical conversations are considered, which neglects the spoken styles in historical speeches.
We propose a spoken style learning approach with multi-modal hierarchical context encoding.
arXiv Detail & Related papers (2021-06-11T08:33:52Z) - SPLAT: Speech-Language Joint Pre-Training for Spoken Language
Understanding [61.02342238771685]
Spoken language understanding requires a model to analyze input acoustic signal to understand its linguistic content and make predictions.
Various pre-training methods have been proposed to learn rich representations from large-scale unannotated speech and text.
We propose a novel semi-supervised learning framework, SPLAT, to jointly pre-train the speech and language modules.
arXiv Detail & Related papers (2020-10-05T19:29:49Z)
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.