English
Related papers

Related papers: Improving CTC-based ASR Models with Gated Interlay…

200 papers

The pre-dominant approach to language modeling to date is based on recurrent neural networks. Their success on this task is often linked to their ability to capture unbounded context. In this paper we develop a finite context approach…

Computation and Language · Computer Science 2017-09-12 Yann N. Dauphin , Angela Fan , Michael Auli , David Grangier

Current two-stage TTS framework typically integrates an acoustic model with a vocoder -- the acoustic model predicts a low resolution intermediate representation such as Mel-spectrum while the vocoder generates waveform from the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-23 Jian Cong , Shan Yang , Lei Xie , Dan Su

Affective Computing (AC) is essential for advancing Artificial General Intelligence (AGI), with emotion recognition serving as a key component. However, human emotions are inherently dynamic, influenced not only by an individual's…

Computation and Language · Computer Science 2025-03-31 Yupei Li , Qiyang Sun , Sunil Munthumoduku Krishna Murthy , Emran Alturki , Björn W. Schuller

We investigate automatic interlinear glossing in low-resource settings. We augment a hard-attentional neural model with embedded translation information extracted from interlinear glossed text. After encoding these translations using large…

Computation and Language · Computer Science 2024-03-14 Changbing Yang , Garrett Nicolai , Miikka Silfverberg

The contemporary visual captioning models frequently hallucinate objects that are not actually in a scene, due to the visual misclassification or over-reliance on priors that resulting in the semantic inconsistency between the visual…

Computer Vision and Pattern Recognition · Computer Science 2022-04-14 Wenqiao Zhang , Haochen Shi , Siliang Tang , Jun Xiao , Qiang Yu , Yueting Zhuang

Traditional spoken language processing involves cascading an automatic speech recognition (ASR) system into text processing models. In contrast, "textless" methods process speech representations without ASR systems, enabling the direct use…

Computation and Language · Computer Science 2024-07-16 Shunsuke Kando , Yusuke Miyao , Jason Naradowsky , Shinnosuke Takamichi

End-to-end Automatic Speech Recognition (ASR) systems based on neural networks have seen large improvements in recent years. The availability of large scale hand-labeled datasets and sufficient computing resources made it possible to train…

Computer Vision and Pattern Recognition · Computer Science 2023-01-05 Maxime Burchi , Radu Timofte

Recently, semantic communication (SC) has been regarded as one of the potential paradigms of 6G. Current SC frameworks require channel state information (CSI) to handle severe signal distortion induced by channel fading. Since the channel…

Information Theory · Computer Science 2023-12-29 Jin Mao , Ke Xiong , Ming Liu , Zhijin Qin , Wei Chen , Pingyi Fan , Khaled Ben Letaief

Popular neural network-based speech enhancement systems operate on the magnitude spectrogram and ignore the phase mismatch between the noisy and clean speech signals. Conditional generative adversarial networks (cGANs) show promise in…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-21 Deepak Baby

While word error rates of automatic speech recognition (ASR) systems have consistently fallen, natural language understanding (NLU) applications built on top of ASR systems still attribute significant numbers of failures to low-quality…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-05 David M. Chan , Shalini Ghosh , Hitesh Tulsiani , Ariya Rastrow , Björn Hoffmeister

Recent advances have witnessed that value decomposed-based multi-agent reinforcement learning methods make an efficient performance in coordination tasks. Most current methods assume that agents can make communication to assist decisions,…

Artificial Intelligence · Computer Science 2021-06-04 Tianze Zhou , Fubiao Zhang , Pan Tang , Chenfei Wang

One common approach for question answering over speech data is to first transcribe speech using automatic speech recognition (ASR) and then employ text-based retrieval-augmented generation (RAG) on the transcriptions. While this cascaded…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-06 Do June Min , Karel Mundnich , Andy Lapastora , Erfan Soltanmohammadi , Srikanth Ronanki , Kyu Han

The acoustic-to-word model based on the connectionist temporal classification (CTC) criterion was shown as a natural end-to-end (E2E) model directly targeting words as output units. However, the word-based CTC model suffers from the…

Computation and Language · Computer Science 2018-03-16 Jinyu Li , Guoli Ye , Amit Das , Rui Zhao , Yifan Gong

Previous work combines word-level and character-level representations using concatenation or scalar weighting, which is suboptimal for high-level tasks like reading comprehension. We present a fine-grained gating mechanism to dynamically…

Computation and Language · Computer Science 2017-09-13 Zhilin Yang , Bhuwan Dhingra , Ye Yuan , Junjie Hu , William W. Cohen , Ruslan Salakhutdinov

Many existing works on voice conversion (VC) tasks use automatic speech recognition (ASR) models for ensuring linguistic consistency between source and converted samples. However, for the low-data resource domains, training a high-quality…

Sound · Computer Science 2023-05-25 Mayank Kumar Singh , Naoya Takahashi , Onoe Naoyuki

Speech recognition in mixed language has difficulties to adapt end-to-end framework due to the lack of data and overlapping phone sets, for example in words such as "one" in English and "w\`an" in Chinese. We propose a CTC-based end-to-end…

Computation and Language · Computer Science 2018-10-31 Genta Indra Winata , Andrea Madotto , Chien-Sheng Wu , Pascale Fung

The rapid development of neural text-to-speech (TTS) systems enabled its usage in other areas of natural language processing such as automatic speech recognition (ASR) or spoken language translation (SLT). Due to the large number of…

Computation and Language · Computer Science 2024-08-01 Nick Rossenbach , Ralf Schlüter , Sakriani Sakti

Although automatic speech recognition (ASR) can perform well in common non-overlapping environments, sustaining performance in multi-talker overlapping speech recognition remains challenging. Recent research revealed that ASR model's…

Sound · Computer Science 2023-03-07 Lingwei Meng , Jiawen Kang , Mingyu Cui , Yuejiao Wang , Xixin Wu , Helen Meng

This paper presents our latest effort on improving Code-switching language models that suffer from data scarcity. We investigate methods to augment Code-switching training text data by artificially generating them. Concretely, we propose a…

Computation and Language · Computer Science 2021-12-14 Chia-Yu Li , Ngoc Thang Vu

We propose a novel approach for ASR N-best hypothesis rescoring with graph-based label propagation by leveraging cross-utterance acoustic similarity. In contrast to conventional neural language model (LM) based ASR rescoring/reranking…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-09 Srinath Tankasala , Long Chen , Andreas Stolcke , Anirudh Raju , Qianli Deng , Chander Chandak , Aparna Khare , Roland Maas , Venkatesh Ravichandran