paper-with-me

Papers

Speech Vecalign: an Embedding-based Method for Aligning Parallel Speech Documents

2025-09-22 · Chutong Meng, Philipp Koehn arxiv

We present Speech Vecalign, a parallel speech document alignment method that monotonically aligns speech segment embeddings and does not depend on text transcriptions. Compared to the baseline method Global Mining, a variant of speech mining, Speech Vecalign produces longer speech-to-speech alignments. It also demonstrates greater robustness than Local Mining, another speech mining variant, as it produces less noise. We applied Speech Vecalign to 3,000 hours of unlabeled parallel English-German (En-De) speech documents from VoxPopuli, yielding about 1,000 hours of high-quality alignments. We then trained En-De speech-to-speech translation models on the aligned data. Speech Vecalign improves the En-to-De and De-to-En performance over Global Mining by 0.37 and 0.18 ASR-BLEU, respectively. Moreover, our models match or outperform SpeechMatrix model performance, despite using 8 times fewer raw speech documents.

📄 PDF Abstract BibTeX arXiv:2509.18360

Code (0)

등록된 구현이 없습니다.

Tasks

Speech-to-Speech Translation

Similar Papers 제목 키워드 기반

Adaptative Bilingual Aligning Using Multilingual Sentence Embedding

2024-03-18 · Olivier Kraif

In this paper, we present an adaptive bitextual alignment system called AIlign. This aligner relies on sentence embeddings to extract reliable anchor points that can guide the alignment path, even for texts whose paralle…

SentenceSentence EmbeddingSentence-EmbeddingSentence Embeddings

DTW-Align: Bridging the Modality Gap in End-to-End Speech Translation with Dynamic Time Warping Alignment

2025-09-23 · Abderrahmane Issam, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis arxiv

End-to-End Speech Translation (E2E-ST) is the task of translating source speech directly into target text bypassing the intermediate transcription step. The representation discrepancy between the speech and text modaliti…

TranSentence: Speech-to-speech Translation via Language-agnostic Sentence-level Speech Encoding without Language-parallel Data

2024-01-17 · Seung-bin Kim, Sang-Hoon Lee, Seong-Whan Lee

Although there has been significant advancement in the field of speech-to-speech translation, conventional models still require language-parallel speech data between the source and target languages for training. In this …

SentenceSpeech-to-Speech TranslationTranslation

Vecalign: Improved Sentence Alignment in Linear Time and Space

2019-11-01 · IJCNLP 2019 11 · Brian Thompson, Philipp Koehn

We introduce Vecalign, a novel bilingual sentence alignment method which is linear in time and space with respect to the number of sentences being aligned and which requires only bilingual sentence embeddings. On a stand…

Machine TranslationSentenceSentence EmbeddingsTranslation

End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning

2019-08-13 · Pavel Denisov, Ngoc Thang Vu

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by tran…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1