Related papers: A Data-Driven Investigation of Noise-Adaptive Utte…

We present a noise-robust adaptation control strategy for block-online supervised acoustic system identification by exploiting a noise dictionary. The proposed algorithm takes advantage of the pronounced spectral structure which…

We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…

The massive amounts of web-mined parallel data contain large amounts of noise. Semantic misalignment, as the primary source of the noise, poses a challenge for training machine translation systems. In this paper, we first introduce a…

Text-to-speech models trained on large-scale datasets have demonstrated impressive in-context learning capabilities and naturalness. However, control of speaker identity and style in these models typically requires conditioning on reference…

Human communication is a collaborative process. Speakers, on top of conveying their own intent, adjust the content and language expressions by taking the listeners into account, including their knowledge background, personalities, and…

Training a spoken language understanding system, as the one in Alexa, typically requires a large human-annotated corpus of data. Manual annotations are expensive and time consuming. In Alexa Skill Kit (ASK) user experience with the skill…

Previous studies show that incorporating external information could improve the translation quality of Neural Machine Translation (NMT) systems. However, there are inevitably noises in the external information, severely reducing the benefit…

Modern virtual personal assistants provide a convenient interface for completing daily tasks via voice commands. An important consideration for these assistants is the ability to recover from automatic speech recognition (ASR) and natural…

This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these…

The ability of a dialog system to express consistent language style during conversations has a direct, positive impact on its usability and on user satisfaction. Although previous studies have demonstrated that style transfer is feasible…

We present a neural model for paraphrasing and train it to generate delexicalized sentences. We achieve this by creating training data in which each input is paired with a number of reference paraphrases. These sets of reference paraphrases…

Paraphrase generation is a longstanding NLP task that has diverse applications for downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised…

One of the most challenging scenarios for smart speakers is multi-talker, when target speech from the desired speaker is mixed with interfering speech from one or more speakers. A smart assistant needs to determine which voice to recognize…

Speech enhancement (SE) methods mainly focus on recovering clean speech from noisy input. In real-world speech communication, however, noises often exist in not only speaker but also listener environments. Although SE methods can suppress…

Speech and voice conditions can alter the acoustic properties of speech, which could impact the performance of paralinguistic models for affect for people with atypical speech. We evaluate publicly available models for recognizing…

An interpretable system for open-domain reasoning needs to express its reasoning process in a transparent form. Natural language is an attractive representation for this purpose -- it is both highly expressive and easy for humans to…

The Lombard effect refers to individuals' unconscious modulation of vocal effort in response to variations in the ambient noise levels, intending to enhance speech intelligibility. The impact of different decibel levels and types of…

While generative methods have progressed rapidly in recent years, generating expressive prosody for an utterance remains a challenging task in text-to-speech synthesis. This is particularly true for systems that model prosody explicitly…

Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in face of various practical environments. However, such…

Artificial Neural Networks are powerful function approximators capable of modelling solutions to a wide variety of problems, both supervised and unsupervised. As their size and expressivity increases, so too does the variance of the model,…