Search Results - "Mosner, Ladislav"

Speech-Based Emotion Recognition with Self-Supervised Models Using Attentive Channel-Wise Correlations and Label Smoothing by Kakouros, Sofoklis, Stafylakis, Themos, Mosner, Ladislav, Burget, Lukas

“…When recognizing emotions from speech, we encounter two common problems: how to optimally capture emotion-relevant information from the speech signal and how…”
Get full text

Improving Noise Robustness of Automatic Speech Recognition via Parallel Data and Teacher-student Learning by Mosner, Ladislav, Wu, Minhua, Raju, Anirudh, Krishnan Parthasarathi, Sree Hari, Kumatani, Kenichi, Sundaram, Shiva, Maas, Roland, Hoffmeister, Bjorn

“…For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique…”
Get full text

13 years of speaker recognition research at BUT, with longitudinal analysis of NIST SRE by Matějka, Pavel, Plchot, Oldřich, Glembek, Ondřej, Burget, Lukáš, Rohdin, Johan, Zeinali, Hossein, Mošner, Ladislav, Silnova, Anna, Novotný, Ondřej, Diez, Mireia, “Honza” Černocký, Jan

“…•We present a “longitudinal study” of all important milestone techniques used in speaker recognition by evaluating on multiple NIST SREs.•We provide aa…”
Get full text

Multisv: Dataset for Far-Field Multi-Channel Speaker Verification by Mosner, Ladislav, Plchot, Oldrich, Burget, Lukas, Cernocky, Jan Honza

“…Motivated by unconsolidated data situation and the lack of a standard benchmark in the field, we complement our previous efforts and present a comprehensive…”
Get full text

Dereverberation and Beamforming in Far-Field Speaker Recognition by Mosner, Ladislav, Matejka, Pavel, Novotny, Ondrej, Cernocky, Jan Honza

“…This paper deals with far-field speaker recognition. On a corpus of NIST SRE 2010 data retransmitted in a real room with multiple microphones, we first…”
Get full text

Parameter-Efficient Transfer Learning of Pre-Trained Transformer Models for Speaker Verification Using Adapters by Peng, Junyi, Stafylakis, Themos, Gu, Rongzhi, Plchot, Oldrich, Mosner, Ladislav, Burget, Lukas, Cernocky, Jan

“…Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various…”
Get full text

Building and evaluation of a real room impulse response dataset by Szoke, Igor, Skacel, Miroslav, Mosner, Ladislav, Paliesek, Jakub, Cernocky, Jan

“…This paper presents BUT ReverbDB-a dataset of real room impulse responses (RIR), background noises, and retransmitted speech data. The retransmitted data…”
Get full text

Multi-Channel Speaker Verification with Conv-Tasnet Based Beamformer by Mosner, Ladislav, Plchot, Oldrich, Burget, Lukas, Cernocky, Jan Honza

“…We focus on the problem of speaker recognition in far-field multichannel data. The main contribution is introducing an alternative way of predicting spatial…”
Get full text

But System for the Second Dihard Speech Diarization Challenge by Landini, Federico, Wang, Shuai, Diez, Mireia, Burget, Lukas, Matejka, Pavel, Zmolikova, Katerina, Mosner, Ladislav, Silnova, Anna, Plchot, Oldrich, Novotny, Ondrej, Zeinali, Hossein, Rohdin, Johan

“…This paper describes the winning systems developed by the BUT team for the four tracks of the Second DIHARD Speech Diarization Challenge. For tracks 1 and 2…”
Get full text

Speech-based emotion recognition with self-supervised models using attentive channel-wise correlations and label smoothing by Kakouros, Sofoklis, Stafylakis, Themos, Mosner, Ladislav, Burget, Lukas

“…When recognizing emotions from speech, we encounter two common problems: how to optimally capture emotion-relevant information from the speech signal and how…”
Get full text

Extracting Speaker and Emotion Information from Self-Supervised Speech Models via Channel-Wise Correlations by Stafylakis, Themos, Mosner, Ladislav, Kakouros, Sofoklis, Plchot, Oldrich, Burget, Lukas, Cernocky, Jan

“…Self-supervised learning of speech representations from large amounts of unlabeled data has enabled state-of-the-art results in several speech processing…”
Get full text

An Attention-Based Backend Allowing Efficient Fine-Tuning of Transformer Models for Speaker Verification by Peng, Junyi, Plchot, Oldrich, Stafylakis, Themos, Mosner, Ladislav, Burget, Lukas, Cernocky, Jan

“…In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks. However, the…”
Get full text

Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations by Stafylakis, Themos, Mosner, Ladislav, Kakouros, Sofoklis, Plchot, Oldrich, Burget, Lukas, Cernocky, Jan

“…Self-supervised learning of speech representations from large amounts of unlabeled data has enabled state-of-the-art results in several speech processing…”
Get full text

An attention-based backend allowing efficient fine-tuning of transformer models for speaker verification by Peng, Junyi, Plchot, Oldrich, Stafylakis, Themos, Mosner, Ladislav, Burget, Lukas, Cernocky, Jan

“…In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks. However, the…”
Get full text

Speaker Verification with Application-Aware Beamforming by Mosner, Ladislav, Plchot, Oldrich, Rohdin, Johan, Burget, Lukas, Cernocky, Jan

“…Multichannel speech processing applications usually employ beamformers as means of speech enhancement through spatial filtering. Beamformers with learnable…”
Get full text

Analysis of Impact of Emotions on Target Speech Extraction and Speech Separation by Svec, Jan, Zmolikova, Katerina, Kocour, Martin, Delcroix, Marc, Ochiai, Tsubasa, Mosner, Ladislav, Cernocky, Jan Honza

“…Recently, the performance of blind speech separation (BSS) and target speech extraction (TSE) has greatly progressed. Most works, however, focus on relatively…”
Get full text

Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch by Silnova, Anna, Stafylakis, Themos, Mosner, Ladislav, Plchot, Oldrich, Rohdin, Johan, Matejka, Pavel, Burget, Lukas, Glembek, Ondrej, Brummer, Niko

“…In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch. We present our…”
Get full text

Building and Evaluation of a Real Room Impulse Response Dataset by Szoke, Igor, Skacel, Miroslav, Mosner, Ladislav, Paliesek, Jakub, Cernocky, Jan "Honza"

“…This paper presents BUT ReverbDB - a dataset of real room impulse responses (RIR), background noises and re-transmitted speech data. The retransmitted data…”
Get full text

State-of-the-art Embeddings with Video-free Segmentation of the Source VoxCeleb Data by Barahona, Sara, Mošner, Ladislav, Stafylakis, Themos, Plchot, Oldřich, Peng, Junyi, Burget, Lukáš, Černocký, Jan

“…In this paper, we refine and validate our method for training speaker embedding extractors using weak annotations. More specifically, we use only the audio…”
Get full text

CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification by Peng, Junyi, Mošner, Ladislav, Zhang, Lin, Plchot, Oldřich, Stafylakis, Themos, Burget, Lukáš, Černocký, Jan

“…Self-supervised learning (SSL) models for speaker verification (SV) have gained significant attention in recent years. However, existing SSL-based SV systems…”
Get full text