awesome-disfluency-detection
github.com/pariajm/awesome-disfluency-detection ↗A curated list of awesome disfluency detection publications along with the released code and bibliographical information
83
GitHub Stars
51
Curated Resources
10
Categories
2 hours ago
Last Refreshed
Noisy Channel ModelsSequence Tagging ModelsTranslation Based ModelsParsing Based ModelsUsing Acoustic/Prosodic CuesData Augmenatation TechniquesIncremental Disfluency DetectionE2E Speech Recognition and Disfluency RemovalE2E Speech Translation and Disfluency RemovalOthers
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me translation based models resources from awesome-disfluency-detection"
Installation instructions →What's inside
Translation Based Models
Others
- Analysis of Disfluency in Children’s Speech.
- Controllable time-delay transformer for real-time punctuation prediction and disfluency detection.
- Disfluencies and human speech transcription errors.
- Disfluent Speech Segments Detection and Remediation.
- Expectation and locality effects in the prediction of disfluent fillers and repairs in English speech.
- Preliminaries to a theory of speech disfluencies.
Noisy Channel Models
Sequence Tagging Models
- A Sequential Repetition Model for Improved Disfluency Detection.
- Disfluency detection using a bidirectional LSTM.
- Disfluency detection using auto-correlational neural networks.
- Joint prediction of punctuation and disfluency in speech transcripts.
- Multi-domain disfluency and repair detection.
- Robust cross-domain disfluency detection with pattern match networks.
Using Acoustic/Prosodic Cues
- Automatic disfluency identification in conversational speech using multiple knowledge sources.
- Automatic punctuation and disfluency detection in multi-party meetings using prosodic and lexical cues.
- Disfluency detection based on speech-aware token-by-token sequence labeling with BLSTM-CRFs and attention mechanisms.
- Giving attention to the unexpected: using prosody innovations in disfluency detection.
- On the role of style in parsing speech with neural models.
- Parsing speech: a neural approach to integrating lexical and acoustic-prosodic information.
Data Augmenatation Techniques
- Auxiliary sequence labeling tasks for disfluency detection.
- Combining self-training and self-supervised learning for unsupervised disfluency detection.
- Disfluency detection with unlabeled data and small BERT models.
- Improving disfluency detection by self-training a self-attentive model.
- Multi-task self-supervised learning for disfluency detection.
- Noisy BiLSTM-based models for disfluency detection.
Parsing Based Models
- Edit detection and parsing for transcribed speech.
- Joint parsing and disfluency detection in linear time.
- Joint transition-based dependency parsing and disfluency detection for automatic speech recognition texts.
- Neural constituency parsing of speech transcripts.
- Semantic parsing of disfluent speech.
- Transition-based disfluency detection using LSTMs.
E2E Speech Recognition and Disfluency Removal
Showing a sample of 51 resources. View the full list on GitHub →