Previous studies demonstrated that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST). However, they required a dedicated model for phone recognition and did not test this solution for direct ST, in which a single model translates the input audio into the target language without intermediate representations. In this work, we propose the first method able to perform a dynamic compression of the input in direct ST models. In particular, we exploit the Connectionist Temporal Classification (CTC) to compress the input sequence according to its phonetic characteristics. Our experiments demonstrate that our solution brings a 1.3-1.5 BLEU improvement over a strong baseline on two language pairs (English-Italian and English-German), contextually reducing the memory footprint by more than 10%
CTC-based Compression for Direct Speech Translation
Marco Gaido;Mauro Cettolo;Matteo Negri
;Marco Turchi
2021-01-01
Abstract
Previous studies demonstrated that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST). However, they required a dedicated model for phone recognition and did not test this solution for direct ST, in which a single model translates the input audio into the target language without intermediate representations. In this work, we propose the first method able to perform a dynamic compression of the input in direct ST models. In particular, we exploit the Connectionist Temporal Classification (CTC) to compress the input sequence according to its phonetic characteristics. Our experiments demonstrate that our solution brings a 1.3-1.5 BLEU improvement over a strong baseline on two language pairs (English-Italian and English-German), contextually reducing the memory footprint by more than 10%File | Dimensione | Formato | |
---|---|---|---|
2021.eacl-main.57.pdf
accesso aperto
Tipologia:
Documento in Post-print
Licenza:
Dominio pubblico
Dimensione
260.1 kB
Formato
Adobe PDF
|
260.1 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.