相关论文: Speech Vecalign: an Embedding-based Method for Ali…

We present a corpus of sentence-aligned triples of German audio, German text, and English translation, based on German audiobooks. The speech translation data consist of 110 hours of audio material aligned to over 50k parallel sentences. An…

This paper presents a novel metric learning approach to address the performance gap between normal and silent speech in visual speech recognition (VSR). The difference in lip movements between the two poses a challenge for existing VSR…

Word and sentence embeddings are useful feature representations in natural language processing. However, intrinsic evaluation for embeddings lags far behind, and there has been no significant update since the past decade. Word and sentence…

The paper presents a novel approach to refining similarity scores between input utterances for robust speaker verification. Given the embeddings from a pair of input utterances, a graph model is designed to incorporate additional…

Recent work has managed to learn cross-lingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training. However, their evaluation has focused on favorable conditions, using…

In this paper, we propose a visual embedding approach to improving embedding aware speech enhancement (EASE) by synchronizing visual lip frames at the phone and place of articulation levels. We first extract visual embedding from lip frames…

We build upon vec2vec, a procedure designed to align text embedding spaces without parallel data. vec2vec finds a near-perfect alignment, but it is expensive and unstable. We present mini-vec2vec, a simple and efficient alternative that…

Static and contextual multilingual embeddings have complementary strengths. Static embeddings, while less expressive than contextual language models, can be more straightforwardly aligned across multiple languages. We combine the strengths…

This work adapts two recent architectures of generative models and evaluates their effectiveness for the conversion of whispered speech to normal speech. We incorporate the normal target speech into the training criterion of…

We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of…

Visual Speech Recognition (VSR) aims to recognize corresponding text by analyzing visual information from lip movements. Due to the high variability and weak information of lip movements, VSR tasks require effectively utilizing any…

We present an easy and efficient method to extend existing sentence embedding models to new languages. This allows to create multilingual versions from previously monolingual models. The training is based on the idea that a translated…

In this paper, we propose a deep convolutional neural network-based acoustic word embedding system on code-switching query by example spoken term detection. Different from previous configurations, we combine audio data in two languages for…

We present improvements to speaker diarization in the two-stage end-to-end neural diarization with vector clustering (EEND-VC) framework. The first stage employs a Conformer-based EEND model with WavLM features to infer frame-level speaker…

We present a novel method for extracting neural embeddings that model the background acoustics of a speech signal. The extracted embeddings are used to estimate specific parameters related to the background acoustic properties of the signal…

Count-based word alignment methods, such as the IBM models or fast-align, struggle on very small parallel corpora. We therefore present an alternative approach based on cross-lingual word embeddings (CLWEs), which are trained on purely…

Multilingual representations pre-trained with monolingual data exhibit considerably unequal task performances across languages. Previous studies address this challenge with resource-intensive contextualized alignment, which assumes the…

Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems , or to perform quality…

While mel-spectrograms have been widely utilized as intermediate representations in zero-shot text-to-speech (TTS), their inherent redundancy leads to inefficiency in learning text-speech alignment. Compact VAE-based latent representations…

Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with…