Image de couverture de livre

Beyond the Labels: Unveiling Text-Dependency in Paralinguistic Speech Recognition Datasets

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pešán, Jan, Kesiraju, Santosh, Burget, Lukáš, Černocký, Jan ''Honza''
Format:	Preprint
Publié:	2024
Sujets:	Audio and Speech Processing Machine Learning Signal Processing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Improving Automatic Speech Recognition with Decoder-Centric Regularisation in Encoder-Decoder Models
par: Polok, Alexander, et autres
Publié: (2024)

DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition
par: Polok, Alexander, et autres
Publié: (2025)

SE-DiCoW: Self-Enrolled Diarization-Conditioned Whisper
par: Polok, Alexander, et autres
Publié: (2026)

ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction
par: Yang, Shu-wen, et autres
Publié: (2025)

Joint Speech and Text Training for LLM-Based End-to-End Spoken Dialogue State Tracking
par: Vendrame, Katia, et autres
Publié: (2025)

Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs
par: Sedláček, Šimon, et autres
Publié: (2025)

Adapting Diarization-Conditioned Whisper for End-to-End Multi-Talker Speech Recognition
par: Kocour, Martin, et autres
Publié: (2025)

Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units
par: Yusuf, Bolaji, et autres
Publié: (2024)

Robustness of Speech Separation Models for Similar-pitch Speakers
par: Lay, Bunlong, et autres
Publié: (2024)

Unsupervised Speech Enhancement using Data-defined Priors
par: Klement, Dominik, et autres
Publié: (2025)

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing
par: Kawamura, Masaya, et autres
Publié: (2025)

Quartered Chirp Spectral Envelope for Whispered vs Normal Speech Classification
par: Joysingh, S. Johanan, et autres
Publié: (2024)

BanglaNum -- A Public Dataset for Bengali Digit Recognition from Speech
par: Mohammad, Mir Sayeed, et autres
Publié: (2024)

CochCeps-Augment: A Novel Self-Supervised Contrastive Learning Using Cochlear Cepstrum-based Masking for Speech Emotion Recognition
par: Ziogas, Ioannis, et autres
Publié: (2024)

DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration
par: Serbest, Sanberk, et autres
Publié: (2025)

Mind the Gap: Impact of Synthetic Conversational Data on Multi-Talker ASR and Speaker Diarization
par: Polok, Alexander, et autres
Publié: (2026)

BUT System for the MLC-SLM Challenge
par: Polok, Alexander, et autres
Publié: (2025)

Speech Watermarking with Discrete Intermediate Representations
par: Ji, Shengpeng, et autres
Publié: (2024)

DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition
par: Polok, Alexander, et autres
Publié: (2024)

GLA-Grad++: An Improved Griffin-Lim Guided Diffusion Model for Speech Synthesis
par: Baoueb, Teysir, et autres
Publié: (2025)

Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads
par: Zaiem, Salah, et autres
Publié: (2023)

A DNN Based Post-Filter to Enhance the Quality of Coded Speech in MDCT Domain
par: Gupta, Kishan, et autres
Publié: (2022)

SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis
par: Baoueb, Teysir, et autres
Publié: (2024)

Lightweight DNN for Full-Band Speech Denoising on Mobile Devices: Exploiting Long and Short Temporal Patterns
par: Drossos, Konstantinos, et autres
Publié: (2025)

State-of-the-art Embeddings with Video-free Segmentation of the Source VoxCeleb Data
par: Barahona, Sara, et autres
Publié: (2024)

Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization
par: Han, Jiangyu, et autres
Publié: (2025)

Efficient and Generalizable Speaker Diarization via Structured Pruning of Self-Supervised Models
par: Han, Jiangyu, et autres
Publié: (2025)

Target Speaker ASR with Whisper
par: Polok, Alexander, et autres
Publié: (2024)

AI-Assisted Music Production: A User Study on Text-to-Music Models
par: Ronchini, Francesca, et autres
Publié: (2025)

Diff-TONE: Timestep Optimization for iNstrument Editing in Text-to-Music Diffusion Models
par: Baoueb, Teysir, et autres
Publié: (2025)

Recovering Performance in Speech Emotion Recognition from Discrete Tokens via Multi-Layer Fusion and Paralinguistic Feature Integration
par: Sun, Esther, et autres
Publié: (2026)

TTSlow: Slow Down Text-to-Speech with Efficiency Robustness Evaluations
par: Gao, Xiaoxue, et autres
Publié: (2024)

Semantic Communications for Speech Recognition
par: Weng, Zhenzi, et autres
Publié: (2021)

VoxKnesset: A Large-Scale Longitudinal Hebrew Speech Dataset for Aging Speaker Modeling
par: Marmor, Yanir, et autres
Publié: (2026)

Bridging the Gap: Integrating Pre-trained Speech Enhancement and Recognition Models for Robust Speech Recognition
par: Wang, Kuan-Chen, et autres
Publié: (2024)

Language Bias in Self-Supervised Learning For Automatic Speech Recognition
par: Storey, Edward, et autres
Publié: (2025)

Overview of the L3DAS23 Challenge on Audio-Visual Extended Reality
par: Marinoni, Christian, et autres
Publié: (2024)

Comparison of Tiny Machine Learning Techniques for Embedded Acoustic Emission Analysis
par: Muthumala, Uditha, et autres
Publié: (2024)

Is Audio Spoof Detection Robust to Laundering Attacks?
par: Ali, Hashim, et autres
Publié: (2024)

Ultra Low Complexity Deep Learning Based Noise Suppression
par: Shetu, Shrishti Saha, et autres
Publié: (2023)