Related papers: A Benchmarking on Cloud based Speech-To-Text Servi…
Machine Translation (MT) has achieved remarkable performance, with growing interest in speech translation and multimodal approaches. However, despite these advancements, MT quality assessment remains largely text centric, typically relying…
Text-to-Speech (TTS) services that run on edge devices have many advantages compared to cloud TTS, e.g., latency and privacy issues. However, neural vocoders with a low complexity and small model footprint inevitably generate annoying…
Contemporary text-to-speech solutions for accessibility applications can typically be classified into two categories: (i) device-based statistical parametric speech synthesis (SPSS) or unit selection (USEL) and (ii) cloud-based neural TTS.…
We present the first text-to-speech (TTS) system tailored to second language (L2) speakers. We use duration differences between American English tense (longer) and lax (shorter) vowels to create a "clarity mode" for Matcha-TTS. Our…
Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech…
Voice-enabled interactions provide more human-like experiences in many popular IoT systems. Cloud-based speech analysis services extract useful information from voice input using speech recognition techniques. The voice signal is a rich…
Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of "domain" adaption to noise. The…
Recently, there has been growth in providers of speech transcription services enabling others to leverage technology they would not normally be able to use. As a result, speech-enabled solutions have become commonplace. Their success…
Statistical TTS systems that directly predict the speech waveform have recently reported improvements in synthesis quality. This investigation evaluates Amazon's statistical speech waveform synthesis (SSWS) system. An in-depth evaluation of…
Token-based text-to-speech (TTS) models have emerged as a promising avenue for generating natural and realistic speech, yet they grapple with low pronunciation accuracy, speaking style and timbre inconsistency, and a substantial need for…
Transformers (Vaswani et al., 2017) have brought a remarkable improvement in the performance of neural machine translation (NMT) systems but they could be surprisingly vulnerable to noise. In this work, we try to investigate how noise…
Modern TTS systems designed for conversations achieve high-quality utterances but often remain inaccessible publicly. Are existing open-source architectures inadequate, or are current training techniques insufficient? This paper…
Full-duplex voice agents--systems that listen and speak simultaneously--are rapidly moving from research to production. However, existing evaluations address conversational dynamics and task completion in isolation. We introduce…
Swiss German is a low-resource language represented by diverse dialects that differ significantly from Standard German and from each other, lacking a standardized written form. As a result, transcribing Swiss German involves translating…
The optimization of a wavelet-based algorithm to improve speech intelligibility along with the full data set and results are reported. The discrete-time speech signal is split into frequency sub-bands via a multi-level discrete wavelet…
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…
Neural machine translation models have shown to achieve high quality when trained and fed with well structured and punctuated input texts. Unfortunately, the latter condition is not met in spoken language translation, where the input is…
Despite Telugu being spoken by over 80 million people, speech translation research for this morphologically rich language remains severely underexplored. We address this gap by developing a high-quality Telugu--English speech translation…
Speech recognition is very challenging in student learning environments that are characterized by significant cross-talk and background noise. To address this problem, we present a bilingual speech recognition system that uses an…
We present a system for non-intrusive prediction of speech quality in noisy and enhanced speech, developed for Track 3 of the VoiceMOS 2024 Challenge. The task required estimating the ITU-T P.835 metrics SIG, BAK, and OVRL without reference…