12 papers
From 2.1M Hours of Raw Broadcast Audio to Finnish Speech SSL: Confidence Filtering and Architectural Analysis at Scale
Yaroslav Getman, Tamás Grósz, Tommi Lehtonen +1
Broadcast archives offer scale and diversity for self-supervised learning (SSL) but contain substantial noisy, non-speech, and multilingual content. Prior work typically relies on…
A Native-Reference Phone-Class Geometry for Second-Language Pronunciation Analysis
Tina Raissi, Nhan Phan, Chenxiao Wang +1
Automatic speaking assessment systems can provide holistic proficiency scores, but often lack interpretable measures that characterize pronunciation quality. We propose a native-re…
A Native-Reference Coordinate Geometry for L2 Pronunciation Deviation Using Self-Supervised Speech Models
Tina Raissi, Nhan Phan, Mikko Kurimo
Self-supervised speech models encode rich phonetic information, but it remains unclear how to transform this information into interpretable metrics for second-language (L2) pronunc…
EmphTTS: an emphasis-control TTS with reinforcement learning
Zirui Li, Rech Silas, Lauri Juvela +2
Generating controllable and human-like emphasis remains an open challenge in text-to-speech, even when explicit emphasis control signals are provided in the text input, limiting th…
CASA: Content-Acoustic Speaking Assessment with Speech Encoder and Large Language Model
Nhan Phan, Ilona Lähteenmäki, Anna von Zansen +4
Research on automatic speaking assessment (ASA) has increasingly adopted multimodal speech large language models to assess learners' speaking performance. However, existing studies…
Autoencoder based optimized SSL representations: Complexity Minimization and improved Dysarthric ASR
Paban Sapkota, Hemant Kumar Kathania, Mikko Kurimo +2
Self-supervised learning (SSL) models extract rich speech representations but often come with high-dimensional features, increasing computational complexity. This work explores an…
Systematic Study of Dysarthric Speech Recognition: Spectral Features and Acoustic Models
Paban Sapkota, Hemant Kumar Kathania, Mikko Kurimo +2
The challenge associated with recognizing dysarthric speech primarily arises from pronounced acoustic variability attributed to impaired articulatory precision. Past research has d…
Nord-Parl-TTS: Finnish and Swedish TTS Dataset from Parliament Speech
Zirui Li, Jens Edlund, Yicheng Gu +3
Text-to-speech (TTS) development is limited by scarcity of high-quality, publicly available speech data for most languages outside a few high-resource languages. We present Nord-Pa…
One Whisper to Grade Them All
Nhan Phan, Anusha Porwal, Yaroslav Getman +3
We present an efficient end-to-end approach for holistic Automatic Speaking Assessment (ASA) of multi-part second-language tests, developed for the 2025 Speak & Improve Challenge.…
Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion Recognition
Mehedi Hasan Bijoy, Dejan Porjazovski, Tamás Grósz +1
Speech Emotion Recognition (SER) is crucial for improving human-computer interaction. Despite strides in monolingual SER, extending them to build a multilingual system remains chal…
Mispronunciation Detection Without L2 Pronunciation Dataset in Low-Resource Setting: A Case Study in Finland Swedish
Nhan Phan, Mikko Kuronen, Maria Kautonen +6
Mispronunciation detection (MD) models are the cornerstones of many language learning applications. Unfortunately, most systems are built for English and other major languages, whi…
Non-native Children's Automatic Speech Assessment Challenge (NOCASA)
Yaroslav Getman, Tamás Grósz, Mikko Kurimo +1
This paper presents the "Non-native Children's Automatic Speech Assessment" (NOCASA) - a data competition part of the IEEE MLSP 2025 conference. NOCASA challenges participants to d…