Search Results for author:
Found 11 papers, 2 papers with code
Language Model Augmented Monotonic Attention for Simultaneous Translation
The state-of-the-art adaptive policies for Simultaneous Neural Machine Translation (SNMT) use monotonic attention to perform read/write decisions based on the partial source and target sequences.
Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection
While crowdsourcing is an established solution for facilitating and scaling the collection of speech data, the involvement of non-experts necessitates protocols to ensure final data quality.
Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond
We present Speech-MASSIVE, a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSIVE textual corpus.
Decision Attentive Regularization to Improve Simultaneous Speech Translation Systems
Hence, read/write decision policy remains the same across different input modalities, i. e., speech and text.
Infusing Future Information into Monotonic Attention Through Language Models
Simultaneous neural machine translation(SNMT) models start emitting the target sequence before they have processed the source sequence.
TASK AWARE MULTI-TASK LEARNING FOR SPEECH TO TEXT TASKS
In general, the direct Speech-to-text translation (ST) is jointly trained with Automatic Speech Recognition (ASR), and Machine Translation (MT) tasks.
Ranked #1 on
Speech-to-Text Translation
on MuST-C EN->DE
(using extra training data)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Learning without Forgetting: Task Aware Multitask Learning for Multi-Modality Tasks
Inspired by these learning patterns in humans, we suggest a simple yet generic task aware framework to incorporate into existing joint learning strategies.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Faster Re-translation Using Non-Autoregressive Model For Simultaneous Neural Machine Translation
The current re-translation approaches are based on autoregressive sequence generation models (ReTA), which generate tar-get tokens in the (partial) translation sequentially.
End-to-End Simultaneous Translation System for IWSLT2020 Using Modality Agnostic Meta-Learning
In this paper, we describe end-to-end simultaneous speech-to-text and text-to-text translation systems submitted to IWSLT2020 online translation challenge.
End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning
In this paper, we describe the system submitted to the IWSLT 2020 Offline Speech Translation Task.
Ranked #3 on
Speech-to-Text Translation
on MuST-C EN->DE
(using extra training data)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
Data Efficient Direct Speech-to-Text Translation with Modality Agnostic Meta-Learning
In the meta-learning phase, the parameters of the model are exposed to vast amounts of speech transcripts (e. g., English ASR) and text translations (e. g., English-German MT).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
