Papers with English speech
Automatic Named Entity Obfuscation in Speech (2023.findings-acl)
Copied to clipboard
| Challenge: | Identifying, replacing and inserting replacement named entities synthesized using voice cloning into original audio reduces the likelihood of deanonymization. |
| Approach: | They propose to use a named entity recognition system built directly on speech to replace a masked language model and synthesize the replacement named entities using voice cloning. |
| Outcome: | The proposed system is built on the English speech NER dataset and tested on a sample of the LibriSpeech corpus. |
Robustness of Multi-Source MT to Transcription Errors (2023.findings-acl)
Copied to clipboard
| Challenge: | In multilingual settings, the same content may be available in various languages via simultaneous interpreting, dubbing or subtitling. |
| Approach: | They hypothesize that leveraging multiple sources will improve translation quality if the sources complement one another in terms of correct information they contain. |
| Outcome: | The proposed method is robust to speech recognition errors on a 10-hour ESIC corpus. |
How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems (2020.acl-main)
Copied to clipboard
| Challenge: | a new study examines how accent information is encoded and propagated in an end-to-end ASR system. |
| Approach: | They propose to use phone probes to analyze phonetic content of representations at each layer. |
| Outcome: | The proposed model is based on a large amount of US-accented English speech and is compared with other models using phone probes. |
Accented Speech Recognition With Accent-specific Codebooks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Degradation in performance across underrepresented accents is a severe deterrent to inclusive adoption of ASR. |
| Approach: | They propose an approach to adapt speech accents to unseen accents by using cross-attention with a trainable set of codebooks. |
| Outcome: | The proposed approach yields significant performance gains on the seen English accents and unseen accents on the Mozilla Common Voice dataset. |
ChiSense-12: An English Sense-Annotated Child-Directed Speech Corpus (2022.lrec-1)
Copied to clipboard
| Challenge: | Recent evidence suggests that the speech children hear early in development is rich in word sense ambiguity, and also that children's early vocabularies are populated by ambiguous words. |
| Approach: | They sense-tagged 53 corpora of American and English speech directed to 958 target children up to 59 months of age and selected target senses that they know young children understand. |
| Outcome: | The sense-tagged corpus ChiSense-12 was used to examine the role of verb-event structure in child word sense disambiguation. |
INTapt: Information-Theoretic Adversarial Prompt Tuning for Enhanced Non-Native Speech Recognition (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to improve ASR performance with pre-trained models require updating the pre-training model weights. |
| Approach: | They propose a method that uses prompts concatenated to the original input to re-modulate attention of the pre-trained model. |
| Outcome: | The proposed model improves the performance of L2 English and increases similarity between L2 and L1 accents. |