no code implementations • 8 Jan 2024 • Tobias Cord-Landwehr, Christoph Boeddeker, Cătălin Zorilă, Rama Doddipatla, Reinhold Haeb-Umbach
We propose a modified teacher-student training for the extraction of frame-wise speaker embeddings that allows for an effective diarization of meeting scenarios containing partially overlapping speech.
no code implementations • 21 Sep 2023 • Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev
Observing that document-grounded response generation via LLMs cannot be adequately assessed by automatic evaluation metrics as they are significantly more verbose, we perform a human evaluation where annotators rate the output of the shared task winning system, the two Chat-GPT variants outputs, and human responses.
no code implementations • 1 Jun 2023 • Simon Keizer, Caroline Dockes, Norbert Braunschweiler, Svetlana Stoyanchev, Rama Doddipatla
Reinforcement learning based dialogue policies are typically trained in interaction with a user simulator.
no code implementations • 1 Jun 2023 • Tobias Cord-Landwehr, Christoph Boeddeker, Cătălin Zorilă, Rama Doddipatla, Reinhold Haeb-Umbach
Using a Teacher-Student training approach we developed a speaker embedding extraction system that outputs embeddings at frame rate.
no code implementations • 1 Jun 2023 • Tobias Cord-Landwehr, Christoph Boeddeker, Cătălin Zorilă, Rama Doddipatla, Reinhold Haeb-Umbach
We introduce a monaural neural speaker embeddings extractor that computes an embedding for each speaker present in a speech mixture.
no code implementations • 24 Apr 2023 • Mohan Li, Rama Doddipatla, Catalin Zorila
In previous works, latency was optimised by truncating the online attention weights based on the hard alignments obtained from conventional ASR models, without taking into account the potential loss of ASR accuracy.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 21 Apr 2023 • Mohan Li, Rama Doddipatla
This paper presents the use of non-autoregressive (NAR) approaches for joint automatic speech recognition (ASR) and spoken language understanding (SLU) tasks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 29 Jul 2022 • Cong-Thanh Do, Mohan Li, Rama Doddipatla
The multiple-hypothesis approach yields a relative reduction of 3. 3% WER on the CHiME-4's single-channel real noisy evaluation set when compared with the single-hypothesis approach.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 9 May 2022 • Catalin Zorila, Rama Doddipatla
Improving the accuracy of single-channel automatic speech recognition (ASR) in noisy conditions is challenging.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 3 May 2022 • Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
In this paper, we explore an improved framework to train a monoaural neural enhancement model for robust speech recognition.
no code implementations • 14 Apr 2022 • Simon Keizer, Norbert Braunschweiler, Svetlana Stoyanchev, Rama Doddipatla
A major bottleneck for building statistical spoken dialogue systems for new domains and applications is the need for large amounts of training data.
no code implementations • 11 Mar 2022 • Mohan Li, Shucong Zhang, Catalin Zorila, Rama Doddipatla
In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 10 Jan 2022 • Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev
Models trained on mixed corpora can be more stable in mismatched contexts, and the performance reductions range from 1 to 8% when compared with single corpus models in matched conditions.
no code implementations • 15 Nov 2021 • Tobias Cord-Landwehr, Christoph Boeddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
Impressive progress in neural network-based single-channel speech source separation has been made in recent years.
no code implementations • 17 Sep 2021 • Suraj Pandey, Svetlana Stoyanchev, Rama Doddipatla
A user input to a schema-driven dialogue information navigation system, such as venue search, is typically constrained by the underlying database which restricts the user to specify a predefined set of preferences, or slots, corresponding to the database fields.
no code implementations • 15 Jun 2021 • Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
The proposed method first uses mixtures of unseparated sources and the mixture invariant training (MixIT) criterion to train a teacher model.
no code implementations • 26 Apr 2021 • Mohan Li, Catalin Zorila, Rama Doddipatla
Online Transformer-based automatic speech recognition (ASR) systems have been extensively studied due to the increasing demand for streaming applications.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 29 Mar 2021 • Cong-Thanh Do, Rama Doddipatla, Thomas Hain
In this method, multiple automatic speech recognition (ASR) 1-best hypotheses are integrated in the computation of the connectionist temporal classification (CTC) loss function.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 9 Feb 2021 • Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals
Although the lower layers of a deep neural network learn features which are transferable across datasets, these layers are not transferable within the same dataset.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 7 Feb 2021 • Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
In this paper, we present a novel multi-channel speech extraction system to simultaneously extract multiple clean individual sources from a mixture in noisy and reverberant environments.
no code implementations • 11 Nov 2020 • Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
To reduce the influence of reverberation on spatial feature extraction, a dereverberation pre-processing method has been applied to further improve the separation performance.
no code implementations • 9 Nov 2020 • Svetlana Stoyanchev, Simon Keizer, Rama Doddipatla
Utterance interpretation is one of the main functions of a dialogue manager, which is the key component of a dialogue system.
1 code implementation • 26 Sep 2019 • Catalin Zorila, Christoph Boeddeker, Rama Doddipatla, Reinhold Haeb-Umbach
Despite the strong modeling power of neural network acoustic models, speech enhancement has been shown to deliver additional word error rate improvements if multi-channel data is available.
no code implementations • 25 Sep 2019 • Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals
Interpreting the top layers as a classifier and the lower layers a feature extractor, one can hypothesize that unwanted network convergence may occur when the classifier has overfit with respect to the feature extractor.
no code implementations • 13 Sep 2015 • Raymond W. M. Ng, Mortaza Doulaty, Rama Doddipatla, Wilker Aziz, Kashif Shah, Oscar Saz, Madina Hasan, Ghada Alharbi, Lucia Specia, Thomas Hain
The USFD primary system incorporates state-of-the-art ASR and MT techniques and gives a BLEU score of 23. 45 and 14. 75 on the English-to-French and English-to-German speech-to-text translation task with the IWSLT 2014 data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4