Challenge: Disfluency removal is an intermediate step between speech recognition and machine translation (MT) with the rise of end-to-end speech translation systems, disfluency recognition and removal needs to be incorporated into the model architectures or handled as a post-processing step.
Approach: They propose to use a sequence-to-sequence model to translate from noisy, disfluent speech to fluent text with disfluencies removed using the recently collected ‘copy-edited’ references for the Fisher Spanish-English dataset.
Outcome: The proposed model generates fluent translations from disfluent speech using the recently collected ‘copy-edited’ references for the Fisher Spanish-English dataset.

Similar Papers

End-to-End Speech Recognition and Disfluency Removal (2020.findings-emnlp)

Copied to clipboard

Challenge: Disfluency detection is usually an intermediate step between an automatic speech recognition system and a downstream task.
Approach: They propose to train models to directly map disfluent speech into fluent transcripts without relying on a separate disfluency detection model.
Outcome: The proposed models learn to generate fluent transcripts, but their performance is slightly worse than a baseline pipeline approach consisting of an ASR system and a specialized disfluency detection model.
Speech Translation and the End-to-End Promise: Taking Stock of Where We Are (2020.acl-main)

Copied to clipboard

Challenge: Until recently, the only feasible approach to translating acoustic speech signals into text was the cascaded approach.
Approach: They propose a classification of the main challenges of traditional approaches to speech translation . they argue that end-to-end models fall short due to compromises made to address data scarcity .
Outcome: This paper provides a brief survey of the main challenges of traditional approaches in speech translation . it reveals that many end-to-end models fail due to compromises made to address data scarcity.
Tutorial: End-to-End Speech Translation (2021.eacl-tutorials)

Copied to clipboard

Challenge: Speech translation is the translation of speech in one language typically to text in another, traditionally accomplished through a combination of automatic speech recognition and machine translation.
Approach: This tutorial introduces the techniques used in cutting-edge research on speech translation.
Outcome: The proposed models achieve state-of-the-art performance with end-to-end speech translation for both high- and low-resource languages.
Investigating the Role and Impact of Disfluency on Summarization (2023.emnlp-industry)

Copied to clipboard

Challenge: Existing studies have focused on disfluency detection and removal, with limited studies into its impact on downstream tasks.
Approach: They propose to incorporate disfluency in summarization models to reduce the impact of replacement disfluencies on natural language processing tasks.
Outcome: The proposed model improves on both public and real-life datasets and shows that it can handle disfluent data with up to 6.99-point degradation in Rouge-L score and replacement disfluencies have the highest negative impact.
Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation (P19-1)

Copied to clipboard

Challenge: Previous work on end-to-end translation from speech uses frame-level features as speech representations, which creates longer, sparser sequences than text.
Approach: They propose a method to generate compressed phoneme-like speech representations that generate shorter, higher-level source sequences for translation.
Outcome: The proposed method improves translation performance by 5 BLEU on high and low resource languages and reduces training time by 60%.
Disfluency Generation for More Robust Dialogue Systems (2023.findings-acl)

Copied to clipboard

Challenge: Disfluencies in user utterances can trigger a chain of errors impacting all the modules of a dialogue system.
Approach: They propose to augment existing dialogue datasets with disfluent utterances by paraphrasing them into disfluente ones.
Outcome: The proposed method improves dialogue state tracking and response generation by combining disfluent utterances with disfluency utteraces.
Simple and Effective Unsupervised Speech Translation (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to train speech models without labeled data are limited for most languages.
Approach: They propose a pipeline approach to build speech translation systems without labeled data by leveraging recent advances in unsupervised speech recognition, machine translation and speech synthesis.
Outcome: The proposed approach outperforms the state-of-the-art in unsupervised speech recognition by 3.2 BLEU on the Libri-Trans benchmark and the best supervised end-to-end models from only two years ago by an average of 5.0 BLUE over five X-En directions.
Disfluent Cues for Enhanced Speech Understanding in Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: a large number of language models struggle to handle disfluencies, authors say . when a speaker hesitates, interrupts themselves, repeats or corrects words, or abandons phrases, it can make their speech fragmented.
Approach: They propose to use disfluent queries to “clean” spontaneous speech . they propose to apply disfluencies to models that use different types of speech repairs .
Outcome: The proposed model improves on a reading comprehension task using disfluent queries . the results suggest that disfluencies can improve model performance, rather than their removal .
Consistent Transcription and Translation of Speech (2020.tacl-1)

Copied to clipboard

Challenge: Existing models that translate without transcribing focus on translation quality, while transcription receives less emphasis.
Approach: They propose a method to evaluate consistency and compare different approaches . they propose 'coupled inference' models that feature a coupled inference procedure can achieve strong consistency.
Outcome: The proposed model is poorly suited to the joint transcription/translation task, but is strong enough to train for consistency.
Dub-S2ST: Textless Speech-to-Speech Translation for Seamless Dubbing (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing speech translation approaches often overlook the transfer of speech patterns, leading to mismatches with source speech and limiting their suitability for dubbing applications.
Approach: They propose a diffusion-based speech-to-unit translation model with explicit duration control that enables time-aligned translation.
Outcome: The proposed system preserves key characteristics such as duration, speaker identity, and speaking speed while maintaining key characteristics.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations