On the integration of speech recognition and statistical machine translation

By Evgeny Matusov, Stephan Kanthak, Hermann Ney. 2005

104 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Direct Speech-to-Speech Translation With Discrete Units (2021, methodology): “Studies on ASR+MT systems explore better ways to integrate ASR output lattice to MT models [15] in order to alleviate the error propagation issue between the two.”
Direct speech-to-speech translation with a sequence-to-sequence model (2019, background): “[5, 6] gave MT access to the lattice of the ASR.”
UWSpeech: Speech to Speech Translation for Unwritten Languages (2020, background): “Previous works on speech translations has evolved from cascaded models [19, 24, 26, 27, 42] to end-to-end models [5, 15, 33, 41, 43], where the text corresponding to speech are leveraged as auxiliary training for better accuracy.”
MAM: Masked Acoustic Modeling for End-to-End Speech-to-Text Translation (2020, unknown): “…scenarios such as international conferences, travels, foreign-language video sub-titling, etc. Conventional cascaded approaches to ST (Ney, 1999; Matusov et al., 2005; Mathias and Byrne, 2006; Berard et al., 2016) ﬁrst transcribe the speech audio into source language text (ASR) and then perform…”
Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation (2022, unknown): “plore the combination of ASR and MT modules [18, 19], as well as TTS modules [1, 20], namely direct S2ST.”
Tied Multitask Learning for Neural Speech Translation (2018, methodology): “For example, Ney (1999) and Matusov et al. (2005) use ASR output lattices as input to translation models, integrating speech recognition uncertainty into the translation model.”
Sequence-to-Sequence Models Can Directly Translate Foreign Speech (2017, methodology): “Early work on speech translation (ST) [14] – translating audio in one language into text in another – used lattices from an ASR system as inputs to translation models [15, 16], giving the translation model access to the speech recognition uncertainty.”
Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation (2018, methodology): “Early work on speech translation typically used a cascade of an ASR model and an MT model [12, 13, 14], giving the MT model access to the predicted probabilities and uncertainties from the ASR.”