mtkresearch / TASTE-SpokenLMLinks
A method that directly addresses the modality gap by aligning speech token with the corresponding text transcription during the tokenization stage.
☆98Updated 2 months ago
Alternatives and similar repositories for TASTE-SpokenLM
Users that are interested in TASTE-SpokenLM are comparing it to the libraries listed below
Sorting:
- Code for DeSTA2.5-Audio☆122Updated 3 months ago
- Code and model for ICASSP 2025 Paper "Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data"☆115Updated 4 months ago
- Official Code for SyllableLM: Learning Coarse Semantic Units for Speech Language Models☆57Updated 4 months ago
- Official code for Interspeech 2023 paper "Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clusterin…☆61Updated 2 years ago
- Official implementation of MelHuBERT☆68Updated last year
- Implementation of Acoustic BPE (Shen et al., 2024), extended for RVQ-based Neural Audio Codecs☆75Updated 4 months ago
- A Benchmark for Evaluating Turn-Taking and Overlap Handling in Full-Duplex Spoken Dialogue Models☆99Updated 2 months ago
- WavReward: Spoken Dialogue Models With Generalist Reward Evaluators☆54Updated 6 months ago
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆103Updated 6 months ago
- Codebase for 'Scaling Rich Style-Prompted Text-to-Speech Datasets'☆143Updated 7 months ago
- A trainer for SNAC (Multi-Scale Neural Audio Codec) has replaced the decoder with Vocos.☆60Updated last year
- The open source code for LLM-Codec☆141Updated last year
- LibriSpeech-Long is a benchmark dataset for long-form speech generation and processing. Released as part of "Long-Form Speech Generation …☆87Updated 10 months ago
- [NeurIPS' 25] Benchmark for evaluating TTS models on complex prosodic, expressiveness, and linguistic challenges.☆176Updated last month
- Sylber: Syllabic Embedding Representation of Speech from Raw Audio☆68Updated 8 months ago
- [ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer☆66Updated last year
- 《SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts》☆77Updated 2 years ago
- ☆58Updated last month
- A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation☆116Updated 2 months ago
- Official release of StyleTalk dataset.☆70Updated last year
- This is the code for paper: XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs. Demos, technical insigh…☆82Updated 2 months ago
- ☆61Updated last year
- The TTSDS benchmark evaluates synthetic speech quality by considering prosody, speaker identity, and intelligibility, comparing these fac…☆69Updated last month
- A large-scale speech corpus introduced in Spark-TTS, built from diverse open-source datasets for training text-to-speech (TTS) systems.☆95Updated 6 months ago
- ☆70Updated last year
- ☆43Updated last year
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆62Updated last year
- Official code for "Semantic-VAE: Semantic-Alignment Latent Representation for Better Speech Synthesis"☆95Updated 3 weeks ago
- Collection of works for evaluating (and analyzing) large audio-language models (LALMs)☆40Updated 3 months ago
- A single-layer, streaming codec model providing SOTA audio quality and discrete tokens designed for superior downstream modelability.☆105Updated 5 months ago