TIMIT

The TIMIT dataset contains a set of phonetically rich recordings of American English speech, used to evaluate speech recognition and phonetic transcription systems.

Papers using TIMIT (42)

Robust Disentangled Variational Speech Representation Learning For Zero-shot Voice Conversion2022 · 28 citesEstimation Of Speaker Age And Height From Speech Signal Using Bi-encoder Transformer Mixture Model2022 · 14 citesDisentangled Speech Representation Learning Based On Factorized Hierarchical Variational Autoencoder With Self-supervised Objective2022 · 12 citesOn Speech Pre-emphasis As A Simple And Inexpensive Method To Boost Speech Enhancement2024 · 7 citesAISHELL6-whisper: A Chinese Mandarin Audio-visual Whisper Speech Dataset with Speech Recognition Baselines2025 · 6 citesEfficient Multi-channel Speech Enhancement With Spherical Harmonics Injection For Directional Encoding2023 · 2 citesBEST-STD: Bidirectional Mamba-enhanced Speech Tokenization For Spoken Term Detection2024 · 1 citesUnsupervised Speech Recognition With N-skipgram And Positional Unigram Matching2023FlowW2N: Whispered-to-Normal Speech Conversion via Flow-Matching2026Single Channel Blind Dereverberation of Speech Signals2025BFA: Real-time Multilingual Text-to-speech Forced Alignment2025Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs2025State-Space Models in Efficient Whispered and Multi-dialect Speech Recognition2025Tradition Or Innovation: A Comparison Of Modern ASR Methods For Forced Alignment2024 · 5 citesComplex Recurrent Variational Autoencoder With Application To Speech Enhancement2022 · 3 citesPhaseperturbation: Speech Data Augmentation Via Phase Perturbation For Automatic Speech Recognition2023 · 2 citesBack To Supervision: Boosting Word Boundary Detection Through Frame Classification2024Hierarchical Modeling Of Spatial Cues Via Spherical Harmonics For Multi-channel Speech Enhancement2023PDPCRN: Parallel Dual-path CRN With Bi-directional Inter-branch Interactions For Multi-channel Speech Enhancement2023Time-frequency Network for Robust Speaker Recognition2023 · 1 citesImproving Deep Attractor Network by BGRU and GMM for Speech Separation2023 · 1 citesTradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment2024 · 1 citesLearning Phone Recognition from Unpaired Audio and Phone Sequences Based on Generative Adversarial Network2022Phoneme Segmentation Using Self-Supervised Speech Models2022EURO: ESPnet Unsupervised ASR Open-source Toolkit2022Enhancing Unsupervised Speech Recognition with Diffusion GANs2023Weakly-supervised forced alignment of disfluent speech using phoneme-level modeling2023Timestamped Embedding-Matching Acoustic-to-Word CTC ASR2023Representation Learning With Hidden Unit Clustering For Low Resource Speech Applications2023PDPCRN: Parallel Dual-Path CRN with Bi-directional Inter-Branch Interactions for Multi-Channel Speech Enhancement2023Hierarchical Modeling of Spatial Cues via Spherical Harmonics for Multi-Channel Speech Enhancement2023Efficient Multi-Channel Speech Enhancement with Spherical Harmonics Injection for Directional Encoding2023Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching2023Improving Whispered Speech Recognition Performance using Pseudo-whispered based Data Augmentation2023PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognition2023On Speech Pre-emphasis as a Simple and Inexpensive Method to Boost Speech Enhancement2024REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR2024Leveraging Self-Supervised Models for Automatic Whispered Speech Recognition2024MaskCycleGAN-based Whisper to Normal Speech Conversion2024Back to Supervision: Boosting Word Boundary Detection through Frame Classification2024BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection2024Quartered Spectral Envelope and 1D-CNN-based Classification of Normally Phonated and Whispered Speech2024