Cover Image

FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Chengyou, Xue, Hongfei, He, Chunjiang, Hu, Jingbin, Wang, Shuiyuan, Wu, Bo, Ji, Yuyu, Zheng, Jimeng, Chen, Ruofei, Zhu, Zhou, Xie, Lei
Format:	Preprint
Published:	2026
Subjects:	Sound Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HumDial-EIBench: A Human-Recorded Multi-Turn Emotional Intelligence Benchmark for Audio Language Models
by: Wang, Shuiyuan, et al.
Published: (2026)

Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR
by: Li, Longhao, et al.
Published: (2025)

Visual Cues Support Robust Turn-taking Prediction in Noise
by: Russell, Sam O'Connor, et al.
Published: (2025)

WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem
by: Wang, Chengyou, et al.
Published: (2026)

Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory
by: Xiao, Yang, et al.
Published: (2026)

Comparative Analysis of Fast and High-Fidelity Neural Vocoders for Low-Latency Streaming Synthesis in Resource-Constrained Environments
by: Yoneyama, Reo, et al.
Published: (2025)

SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization
by: Chen, Wenxi, et al.
Published: (2025)

SynthVC: Leveraging Synthetic Data for End-to-End Low Latency Streaming Voice Conversion
by: Guo, Zhao, et al.
Published: (2025)

Seeing the Context: Rich Visual Context-Aware Speech Recognition via Multimodal Reasoning
by: Tian, Wenjie, et al.
Published: (2026)

Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics
by: Arora, Siddhant, et al.
Published: (2025)

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages
by: Shao, Mingchen, et al.
Published: (2025)

StreamVC: Real-Time Low-Latency Voice Conversion
by: Yang, Yang, et al.
Published: (2024)

DualTurn: Learning Turn-Taking from Dual-Channel Generative Speech Pretraining
by: Rajaa, Shangeth
Published: (2026)

DualVC 2: Dynamic Masked Convolution for Unified Streaming and Non-Streaming Voice Conversion
by: Ning, Ziqian, et al.
Published: (2023)

Streaming Speech Recognition with Decoder-Only Large Language Models and Latency Optimization
by: Wan, Genshun, et al.
Published: (2026)

MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios
by: Wang, Shuai, et al.
Published: (2025)

WhisperRT -- Turning Whisper into a Causal Streaming Model
by: Krichli, Tomer, et al.
Published: (2025)

Prompt-Guided Turn-Taking Prediction
by: Inoue, Koji, et al.
Published: (2025)

HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement
by: Hussein, Amir, et al.
Published: (2025)

Ultra-Low Latency Speech Enhancement - A Comprehensive Study
by: Wu, Haibin, et al.
Published: (2024)

TurnGuide: Enhancing Meaningful Full Duplex Spoken Interactions via Dynamic Turn-Level Text-Speech Interleaving
by: Cui, Wenqian, et al.
Published: (2025)

LALM-as-a-Judge: Benchmarking Large Audio-Language Models for Safety Evaluation in Multi-Turn Spoken Dialogues
by: Ivry, Amir, et al.
Published: (2026)

LL-SDR: Low-Latency Speech enhancement through Discrete Representations
by: Li, Jingyi, et al.
Published: (2026)

Phoenix-VAD: Streaming Semantic Endpoint Detection for Full-Duplex Speech Interaction
by: Wu, Weijie, et al.
Published: (2025)

Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting
by: Tsunoo, Emiru, et al.
Published: (2025)

CodecBench: A Comprehensive Benchmark for Acoustic and Semantic Evaluation
by: Deng, Ruifan, et al.
Published: (2025)

Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction
by: Dai, Wang, et al.
Published: (2025)

StreamVoice+: Evolving into End-to-end Streaming Zero-shot Voice Conversion
by: Wang, Zhichao, et al.
Published: (2024)

Investigation of Deep Neural Network Acoustic Modelling Approaches for Low Resource Accented Mandarin Speech Recognition
by: Xie, Xurong, et al.
Published: (2022)

Exploring Efficient Directional and Distance Cues for Regional Speech Separation
by: Jiang, Yiheng, et al.
Published: (2025)

Improving Acoustic Scene Classification in Low-Resource Conditions
by: Chen, Zhi, et al.
Published: (2024)

RAVSS: Robust Audio-Visual Speech Separation in Multi-Speaker Scenarios with Missing Visual Cues
by: Pan, Tianrui, et al.
Published: (2024)

PersonaTAB: Predicting Personality Traits using Textual, Acoustic, and Behavioral Cues in Fully-Duplex Speech Dialogs
by: Inoue, Sho, et al.
Published: (2025)

Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion
by: Wang, Jinhan, et al.
Published: (2024)

Whisper Turns Stronger: Augmenting Wav2Vec 2.0 for Superior ASR in Low-Resource Languages
by: Anidjar, Or Haim, et al.
Published: (2024)

FleSpeech: Flexibly Controllable Speech Generation with Various Prompts
by: Li, Hanzhao, et al.
Published: (2025)

Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR
by: Lin, Zhennan, et al.
Published: (2026)

Multilingual Turn-taking Prediction Using Voice Activity Projection
by: Inoue, Koji, et al.
Published: (2024)

Fast-Converging Distributed Signal Estimation in Topology-Unconstrained Wireless Acoustic Sensor Networks
by: Didier, Paul, et al.
Published: (2025)

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty
by: Xue, Hongfei, et al.
Published: (2025)