Related papers: Using phonetic constraints in acoustic-to-articula…
We present a novel computational scheme to solve acoustic wave transmission problems over composite scatterers, i.e. penetrable obstacles possessing junctions or triple points. Our continuous problem is cast as a multiple traces time-domain…
We present an end-to-end method for transforming audio from one style to another. For the case of speech, by conditioning on speaker identities, we can train a single model to transform words spoken by multiple people into multiple target…
Thousands of individuals need surgical removal of their larynx due to critical diseases every year and therefore, require an alternative form of communication to articulate speech sounds after the loss of their voice box. This work…
Despite the rapid progress of automatic speech recognition (ASR) technologies targeting normal speech in recent decades, accurate recognition of dysarthric and elderly speech remains highly challenging tasks to date. Sources of…
In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing spoken utterances, we introduce a model that integrates transcribed text and acoustic-prosodic features…
Domain shift is considered a challenge in machine learning as it causes significant degradation of model performance. In the Acoustic Scene Classification task (ASC), domain shift is mainly caused by different recording devices. Several…
As a category of transfer learning, domain adaptation plays an important role in generalizing the model trained in one task and applying it to other similar tasks or settings. In speech enhancement, a well-trained acoustic model can be…
Accent conversion has rapidly progressed alongside growing interest in improving global cross-cultural communication. This survey presents an overview of the evolution of accent conversion methodologies, analyzing how the field has…
In the case of multi-parameter full-waveform inversion, the computation of the additional Hessian terms that contain derivatives with respect to more than one type of parameter is necessary. If a simple gradient-based minimization is used,…
This paper presents a new voice conversion model capable of transforming both speaking and singing voices. It addresses key challenges in current systems, such as conveying emotions, managing pronunciation and accent changes, and…
In this work, we investigate the effectiveness of pretrained Self-Supervised Learning (SSL) features for learning the mapping for acoustic to articulatory inversion (AAI). Signal processing-based acoustic features such as MFCCs have been…
The inversion of electromagnetic induction data to a conductivity profile is an ill-posed problem. Regularization improves the stability of the inversion and, based on Occam's razor principle, a smoothing constraint is typically used.…
Many mispronunciation detection and diagnosis (MD&D) research approaches try to exploit both the acoustic and linguistic features as input. Yet the improvement of the performance is limited, partially due to the shortage of large amount…
In ultrasound tomography, the speed of sound inside an object is estimated based on acoustic measurements carried out by sensors surrounding the object. An accurate forward model is a prominent factor for high-quality image reconstruction,…
The objective of this work is to train noise-robust speaker embeddings adapted for speaker diarisation. Speaker embeddings play a crucial role in the performance of diarisation systems, but they often capture spurious information such as…
Vocoders are models capable of transforming a low-dimensional spectral representation of an audio signal, typically the mel spectrogram, to a waveform. Modern speech generation pipelines use a vocoder as their final component. Recent…
Recently, voice conversion (VC) has been widely studied. Many VC systems use disentangle-based learning techniques to separate the speaker and the linguistic content information from a speech signal. Subsequently, they convert the voice by…
This paper presents trainable methods for generating letter to sound rules from a given lexicon for use in pronouncing out-of-vocabulary words and as a method for lexicon compression. As the relationship between a string of letters and a…
Voice disorders affect a large portion of the population, especially heavy voice users such as teachers or call-center workers. Most voice disorders can be treated effectively with behavioral voice therapy, which teaches patients to replace…
Unsupervised representation learning for speech audios attained impressive performances for speech recognition tasks, particularly when annotated speech is limited. However, the unsupervised paradigm needs to be carefully designed and…