Imagen de Portada

Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Haoyang, Liu, Hexin, Zhang, Xiangyu, Zhang, Qiquan, Hu, Yuchen, Zhao, Junqi, Tian, Fei, Yang, Xuerui, Garcia, Leibny Paola, Chng, Eng Siong
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Sound Audio and Speech Processing 68T10 I.2.7
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling
por: Yao, Jixun, et al.
Publicado: (2025)

EASY: Emotion-aware Speaker Anonymization via Factorized Distillation
por: Yao, Jixun, et al.
Publicado: (2025)

Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives
por: Liu, Hexin, et al.
Publicado: (2025)

Aligning Speech to Languages to Enhance Code-switching Speech Recognition
por: Liu, Hexin, et al.
Publicado: (2024)

LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation
por: Luong, Hieu-Thi, et al.
Publicado: (2024)

Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model
por: Zhang, Xiangyu, et al.
Publicado: (2024)

Noise-Aware Speech Separation with Contrastive Learning
por: Zhang, Zizheng, et al.
Publicado: (2023)

Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization
por: Hu, Yuchen, et al.
Publicado: (2024)

UniArray: Unified Spectral-Spatial Modeling for Array-Geometry-Agnostic Speech Separation
por: Chen, Weiguang, et al.
Publicado: (2025)

MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models
por: Deng, Yayue, et al.
Publicado: (2025)

Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR
por: Hu, Yuchen, et al.
Publicado: (2023)

Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback
por: Chen, Chen, et al.
Publicado: (2024)

Noise-aware Speech Enhancement using Diffusion Probabilistic Model
por: Hu, Yuchen, et al.
Publicado: (2023)

Mamba in Speech: Towards an Alternative to Self-Attention
por: Zhang, Xiangyu, et al.
Publicado: (2024)

Speech Enhancement Using Continuous Embeddings of Neural Audio Codec
por: Li, Haoyang, et al.
Publicado: (2025)

Robust Localization of Partially Fake Speech: Metrics and Out-of-Domain Evaluation
por: Luong, Hieu-Thi, et al.
Publicado: (2025)

Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs
por: Yuhang, Yang, et al.
Publicado: (2024)

When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection
por: Zhang, Xiangyu, et al.
Publicado: (2024)

Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods
por: Mu, Bingshen, et al.
Publicado: (2025)

Analysis of Speaker Verification Performance Trade-offs with Neural Audio Codec Transmission
por: Thakur, Nirmalya Mallick, et al.
Publicado: (2025)

SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model
por: Qian, Xinyuan, et al.
Publicado: (2024)

Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech
por: Li, Yuxin, et al.
Publicado: (2025)

Towards Audio Codec-based Speech Separation
por: Yip, Jia Qi, et al.
Publicado: (2024)

Audio Large Language Models Can Be Descriptive Speech Quality Evaluators
por: Chen, Chen, et al.
Publicado: (2025)

Noro: Noise-Robust One-shot Voice Conversion with Hidden Speaker Representation Learning
por: He, Haorui, et al.
Publicado: (2024)

Training-Free Intelligibility-Guided Observation Addition for Noisy ASR
por: Li, Haoyang, et al.
Publicado: (2026)

Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR
por: Peng, Yizhou, et al.
Publicado: (2025)

Room Impulse Responses help attackers to evade Deep Fake Detection
por: Luong, Hieu-Thi, et al.
Publicado: (2024)

Dataset-Distillation Generative Model for Speech Emotion Recognition
por: Ritter-Gutierrez, Fabian, et al.
Publicado: (2024)

Continual Learning Optimizations for Auto-regressive Decoder of Multilingual ASR systems
por: Kwok, Chin Yuen, et al.
Publicado: (2024)

Say More with Less: Variable-Frame-Rate Speech Tokenization via Adaptive Clustering and Implicit Duration Coding
por: Zheng, Rui-Chen, et al.
Publicado: (2025)

Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding
por: Ng, Dianwen, et al.
Publicado: (2025)

Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Automatic Speaker Verification
por: Truong, Duc-Tuan, et al.
Publicado: (2023)

Universal Speech Content Factorization
por: Xinyuan, Henry Li, et al.
Publicado: (2026)

SpeechAccentLLM: A Unified Framework for Foreign Accent Conversion and Text to Speech
por: Cheng, Zhuangfei, et al.
Publicado: (2025)

ShiftySpeech: A Large-Scale Synthetic Speech Dataset with Distribution Shifts
por: Garg, Ashi, et al.
Publicado: (2025)

Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection
por: Truong, Duc-Tuan, et al.
Publicado: (2024)

Can LLMs Help Localize Fake Words in Partially Fake Speech?
por: Zhang, Lin, et al.
Publicado: (2026)

ChildMandarin: A Comprehensive Mandarin Speech Dataset for Young Children Aged 3-5
por: Zhou, Jiaming, et al.
Publicado: (2024)

Multilingual Stutter Event Detection for English, German, and Mandarin Speech
por: Haas, Felix, et al.
Publicado: (2026)