Related papers: A Comparative Evaluation of Pitch Modification Tec…
The subjective evaluation of music generation techniques has been mostly done with questionnaire-based listening tests while ignoring the perspectives from music composition, arrangement, and soundtrack editing. In this paper, we propose an…
Decision making is an important component in a speaker verification system. For the conventional GMM-UBM architecture, the decision is usually conducted based on the log likelihood ratio of the test utterance against the GMM of the claimed…
This paper presents a neural vocoder based on a denoising diffusion probabilistic model (DDPM) incorporating explicit periodic signals as auxiliary conditioning signals. Recently, DDPM-based neural vocoders have gained prominence as…
In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…
The speech-to-singing (STS) voice conversion task aims to generate singing samples corresponding to speech recordings while facing a major challenge: the alignment between the target (singing) pitch contour and the source (speech) content…
Speech enhancement is a demanding task in automated speech processing pipelines, focusing on separating clean speech from noisy channels. Transformer based models have recently bested RNN and CNN models in speech enhancement, however at the…
Objective evaluation of audio processed with Time-Scale Modification (TSM) remains an open problem. Recently, a dataset of time-scaled audio with subjective quality labels was published and used to create an initial objective measure of…
Diffusion Probabilistic Models (DPMs) are a well-established class of diffusion models for unconditional image generation, while SGMSE+ is a well-established conditional diffusion model for speech enhancement. One of the downsides of…
Automatic height and age estimation of speakers using acoustic features is widely used for the purpose of human-computer interaction, forensics, etc. In this work, we propose a novel approach of using attention mechanism to build an…
Building multispeaker neural network-based text-to-speech synthesis systems commonly relies on the availability of large amounts of high quality recordings from each speaker and conditioning the training process on the speaker's identity or…
Text-to-Speech synthesis systems are generally evaluated using Mean Opinion Score (MOS) tests, where listeners score samples of synthetic speech on a Likert scale. A major drawback of MOS tests is that they only offer a general measure of…
This paper presents the comparison of compression algorithms for voice transferring method over SMS in satellite communication. Voice transferring method over SMS is useful in situations when signal strength is low and due to poor signal…
Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate…
Fine-tuning is a popular method for adapting text-to-speech (TTS) models to new speakers. However this approach has some challenges. Usually fine-tuning requires several hours of high quality speech per speaker. There is also that…
In a hybrid speech model, both voiced and unvoiced components can coexist in a segment. Often, the voiced speech is regarded as the deterministic component, and the unvoiced speech and additive noise are the stochastic components.…
When translating words referring to the speaker, speech translation (ST) systems should not resort to default masculine generics nor rely on potentially misleading vocal traits. Rather, they should assign gender according to the speakers'…
The performance of speaker recognition system is highly dependent on the amount of speech used in enrollment and test. This work presents a detailed experimental review and analysis of the GMM-SVM based speaker recognition system in…
The widespread of powerful personal devices capable of collecting voice of their users has opened the opportunity to build speaker adapted speech recognition system (ASR) or to participate to collaborative learning of ASR. In both cases,…
Neural text-to-speech (TTS) can provide quality close to natural speech if an adequate amount of high-quality speech material is available for training. However, acquiring speech data for TTS training is costly and time-consuming,…
Large Language Models (LLMs) still produce gender-stereotyped language even in occupation-neutral contexts that reflect deep societal biases (Rudinger et al., 2018). To address this, prior work has proposed prompting, constrained decoding…