English datasets

The 'English datasets' benchmark contains various datasets used to evaluate the performance and security of speech synthesis systems, particularly in the context of adversarial attacks and defenses.

Papers using English datasets (33)

LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context2025 · 3 citesBreaking the Script Barrier: Enabling Automatic Alignment for PoS-based ASR Error Analysis in Non-Latin Scripts2026Accent-Invariant Automatic Speech Recognition via Saliency-Driven Spectrogram Masking2025 · 2 citesWord stress in self-supervised speech models: A cross-linguistic comparison2025 · 2 citesExploring Cross-Lingual Voice Conversion Methods for Anonymizing Low-Resource Text-to-Speech2026Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs2026An Ultra-Low Latency, End-to-End Streaming Speech Synthesis Architecture via Block-Wise Generation and Depth-Wise Codec Decoding2026Utterance-Level Methods for Identifying Reliable ASR-Output for Child Speech2026findsylls: A Language-Agnostic Toolkit for Syllable-Level Speech Tokenization and Embedding2026Unsupervised Cross-Lingual Part-of-Speech Tagging with Monolingual Corpora Only2026E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis2025Unsupervised lexicon learning from speech is limited by representations rather than clustering2025Parallel GPT: Harmonizing the Independence and Interdependence of Acoustic and Semantic Information for Zero-Shot Text-to-Speech2025SpeechDialogueFactory: Generating High-Quality Speech Dialogue Data to Accelerate Your Speech-LLM Development2025Evaluating Standard and Dialectal Frisian ASR: Multilingual Fine-tuning and Language Identification for Improved Low-resource Performance2025Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptions2023 · 2 citesEditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion2021 · 1 citesAnalysis of Voice Conversion and Code-Switching Synthesis Using VQ-VAE2022 · 1 citesAnalyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models2022 · 1 citesTTS-Guided Training for Accent Conversion Without Parallel Data2022 · 1 citesSyllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model2023 · 1 citesParaformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition2024 · 1 citesAdvocating Character Error Rate for Multilingual ASR Evaluation2024 · 1 citesSTTATTS: Unified Speech-To-Text And Text-To-Speech Model2024 · 1 citesIntent Classification Using Pre-trained Language Agnostic Embeddings For Low Resource Languages2021Visually Grounded Keyword Detection and Localisation for Low-Resource Languages2023Learning Multilingual Expressive Speech Representation for Prosody Prediction without Parallel Data2023Zero Resource Cross-Lingual Part Of Speech Tagging2024Contextualized Automatic Speech Recognition with Dynamic Vocabulary2024VECL-TTS: Voice identity and Emotional style controllable Cross-Lingual Text-to-Speech2024Enhancing Polyglot Voices by Leveraging Cross-Lingual Fine-Tuning in Any-to-One Voice Conversion2024Textless NLP -- Zero Resource Challenge with Low Resource Compute2024LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech2023