jasonppy / word-discoveryLinks
Word Discovery in Visually Grounded, Self-Supervised Speech Models
☆26Updated last year
Alternatives and similar repositories for word-discovery
Users that are interested in word-discovery are comparing it to the libraries listed below
Sorting:
- Transformer-based visually grounded speech models☆19Updated 2 years ago
- This repo contains the official PyTorch implementation of "Analyzing Discrete Self Supervised Speech Representation For Spoken Language M…☆18Updated 2 years ago
- ☆36Updated 2 years ago
- Official code for Interspeech 2023 paper "Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clusterin…☆52Updated 2 years ago
- Official Code for SyllableLM: Learning Coarse Semantic Units for Speech Language Models☆55Updated last month
- Unsupervised phone and word segmentation using dynamic programming on self-supervised VQ features.☆37Updated last year
- (Hybrid) BYOL-S feature extractor using serab-byols package in pytorch.☆27Updated last year
- ☆30Updated 6 months ago
- DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning☆49Updated last year
- Syllable Segmentation and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model☆32Updated last year
- A collection of papers related to speech model compression☆26Updated last year
- ☆31Updated last year
- Code for T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5☆19Updated 2 years ago
- SpeechGLUE is a speech version of the GLUE benchmark, driven by text-to-speech.☆13Updated 2 years ago
- A benchmark to evaluate full-duplex spoken dialogue models on pause handling, backchanneling, turn-taking, and user interruptions.☆32Updated 2 weeks ago
- (Interspeech 2023 & ICASSP 2024) Official repository for ARMHuBERT and STaRHuBERT☆40Updated 9 months ago
- Official implementation of MelHuBERT☆65Updated 7 months ago
- 56 language, 1 model Multilingual ASR☆25Updated 3 years ago
- Speech-MASSIVE is a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSI…☆22Updated 9 months ago
- Official code for Wav2Seq☆96Updated 2 years ago
- A spoken version of the textual story cloze benchmark☆17Updated last year
- ☆38Updated last week
- SLMTokBench for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"☆35Updated last year
- Audio-visual diarization pipeline used for creating VoxConverse dataset☆21Updated 3 months ago
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆13Updated 2 years ago
- Code repository for the paper "Improving End-to-End SLU performance with Prosodic Attention and Distillation" accepted at Interspeech 202…☆26Updated 2 years ago
- multilingual speech aligner☆74Updated last year
- This repository presents an evaluation framework for speech-to-speech (S2S) models, following the methodology described in the EmphAsses …☆21Updated last year
- Transcribing Speech with Multinomial Diffusion, training code and models.☆76Updated last year
- ☆39Updated 8 months ago