Related papers: Cross-lingual topic prediction for speech using tr…

Recent foundational language models have shown state-of-the-art performance in many NLP tasks in zero- and few-shot settings. An advantage of these models over more standard approaches based on fine-tuning is the ability to understand…

We present a neural network architecture based on bidirectional LSTMs to compute representations of words in the sentential contexts. These context-sensitive word representations are suitable for, e.g., distinguishing different word senses…

Level assessment for foreign language students is necessary for putting them in the right level group, furthermore, interviewing students is a very time-consuming task, so we propose to automate the evaluation of speaker fluency level by…

Voice conversion (VC) could be used to improve speech recognition systems in low-resource languages by using it to augment limited training data. However, VC has not been widely used for this purpose because of practical issues such as…

Learned metrics such as BLEURT have in recent years become widely employed to evaluate the quality of machine translation systems. Training such metrics requires data which can be expensive and difficult to acquire, particularly for…

Recent studies on direct speech translation show continuous improvements by means of data augmentation techniques and bigger deep learning models. While these methods are helping to close the gap between this new approach and the more…

Use of speech models for automatic speech processing tasks can improve efficiency in the screening, analysis, diagnosis and treatment in medicine and psychiatry. However, the performance of pre-processing speech tasks like segmentation and…

Data scarcity in low-resource languages can be addressed with word-to-word translations from labeled task data in high-resource languages using bilingual lexicons. However, bilingual lexicons often have limited lexical overlap with task…

Text classification tends to be difficult when data are deficient or when it is required to adapt to unseen classes. In such challenging scenarios, recent studies have often used meta-learning to simulate the few-shot task, thus negating…

Human listeners readily adjust to unfamiliar speakers and language varieties through exposure, but do these adaptation benefits extend to state-of-the-art spoken language models? We introduce a scalable framework that allows for in-context…

Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks. For example in speech recognition, an acoustic model trained for one language can be used to recognize speech in…

This work investigates the use of natural language to enable zero-shot model adaptation to new tasks. We use text and metadata from social commenting platforms as a source for a simple pretraining task. We then provide the language model…

Distinguishing scripted from spontaneous speech is an essential tool for better understanding how speech styles influence speech processing research. It can also improve recommendation systems and discovery experiences for media users…

Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the…

This paper presents a method for end-to-end cross-lingual text-to-speech (TTS) which aims to preserve the target language's pronunciation regardless of the original speaker's language. The model used is based on a non-attentive Tacotron…

Zero-shot cross-lingual transfer is when a multilingual model is trained to perform a task in one language and then is applied to another language. Although the zero-shot cross-lingual transfer approach has achieved success in various…

In an attempt to improve overall translation quality, there has been an increasing focus on integrating more linguistic elements into Machine Translation (MT). While significant progress has been achieved, especially recently with neural…

Sentiment classification involves quantifying the affective reaction of a human to a document, media item or an event. Although researchers have investigated several methods to reliably infer sentiment from lexical, speech and body language…

Topic models are widely used in natural language processing, allowing researchers to estimate the underlying themes in a collection of documents. Most topic models use unsupervised methods and hence require the additional step of attaching…

Large Language Models (LLMs) have demonstrated remarkable success across a wide range of tasks and domains. However, their performance in low-resource language translation, particularly when translating into these languages, remains…