A hierarchical transducer with self-distillation and a tuned blank penalty improves joint speech recognition and translation, matching offline attention models on conversational data.
Advancing Speech Translation: A Corpus of Mandarin-English Conversational Telephone Speech
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper introduces a set of English translations for a 123-hour subset of the CallHome Mandarin Chinese data and the HKUST Mandarin Telephone Speech data for the task of speech translation. Paired source-language speech and target-language text is essential for training end-to-end speech translation systems and can provide substantial performance improvements for cascaded systems as well, relative to training on more widely available text data sets. We demonstrate that fine-tuning a general-purpose translation model to our Mandarin-English conversational telephone speech training set improves target-domain BLEU by more than 8 points, highlighting the importance of matched training data.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation
A hierarchical transducer with self-distillation and a tuned blank penalty improves joint speech recognition and translation, matching offline attention models on conversational data.