Related papers: Deep Feed-forward Sequential Memory Networks for S…

Despite the close relationship between speech perception and production, research in automatic speech recognition (ASR) and text-to-speech synthesis (TTS) has progressed more or less independently without exerting much mutual influence on…

Long Short-Term Memory (LSTM) is a popular approach to boosting the ability of Recurrent Neural Networks to store longer term temporal information. The capacity of an LSTM network can be increased by widening and adding layers. However,…

Synthetically generated speech has rapidly approached human levels of naturalness. However, the paradox remains that ASR systems, when trained on TTS output that is judged as natural by humans, continue to perform badly on real speech. In…

Recent works have shown that Deep Recurrent Neural Networks using the LSTM architecture can achieve strong single-channel speech enhancement by estimating time-frequency masks. However, these models do not naturally generalize to…

Direct Speech-to-Speech Translation (S2ST) has gained increasing attention for its ability to translate speech from one language to another, while reducing error propagation and latency inherent in traditional cascaded pipelines. However,…

In this paper, a novel architecture for a deep recurrent neural network, residual LSTM is introduced. A plain LSTM has an internal memory cell that can learn long term dependencies of sequential data. It also provides a temporal shortcut…

We propose a method using a long short-term memory (LSTM) network to estimate the noise power spectral density (PSD) of single-channel audio signals represented in the short time Fourier transform (STFT) domain. An LSTM network common to…

Most existing text-to-speech (TTS) systems either synthesize speech sentence by sentence and stitch the results together, or drive synthesis from plain-text dialogues alone. Both approaches leave models with little understanding of global…

Data analytics helps basketball teams to create tactics. However, manual data collection and analytics are costly and ineffective. Therefore, we applied a deep bidirectional long short-term memory (BLSTM) and mixture density network (MDN)…

With the development of speech synthesis techniques, automatic speaker verification systems face the serious challenge of spoofing attack. In order to improve the reliability of speaker verification systems, we develop a new filter bank…

Trans-dimensional random field language models (TRF LMs) have recently been introduced, where sentences are modeled as a collection of random fields. The TRF approach has been shown to have the advantages of being computationally more…

In this paper, we propose a deep neural network approach for deepfake speech detection (DSD) based on a lowcomplexity Depthwise-Inception Network (DIN) trained with a contrastive training strategy (CTS). In this framework, input audio…

Confidence estimation, in which we estimate the reliability of each recognized token (e.g., word, sub-word, and character) in automatic speech recognition (ASR) hypotheses and detect incorrectly recognized tokens, is an important function…

While neural-based text to speech (TTS) models can synthesize natural and intelligible voice, they usually require high-quality speech data, which is costly to collect. In many scenarios, only noisy speech of a target speaker is available,…

In this paper we investigate the GMM-derived (GMMD) features for adaptation of deep neural network (DNN) acoustic models. The adaptation of the DNN trained on GMMD features is done through the maximum a posteriori (MAP) adaptation of the…

Speech synthesis is an important practical generative modeling problem that has seen great progress over the last few years, with likelihood-based autoregressive neural models now outperforming traditional concatenative systems. A downside…

We present a novel model designed for resource-efficient multichannel speech enhancement in the time domain, with a focus on low latency, lightweight, and low computational requirements. The proposed model incorporates explicit spatial and…

The use of low numerical precision is a fundamental optimization included in modern accelerators for Deep Neural Networks (DNNs). The number of bits of the numerical representation is set to the minimum precision that is able to retain…

End-to-end text-to-speech synthesis systems achieved immense success in recent times, with improved naturalness and intelligibility. However, the end-to-end models, which primarily depend on the attention-based alignment, do not offer an…

This paper proposes a deep neural network model for joint modeling Natural Language Understanding (NLU) and Dialogue Management (DM) in goal-driven dialogue systems. There are three parts in this model. A Long Short-Term Memory (LSTM) at…