Search Results for author:
Found 25 papers, 2 papers with code
UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models
UniEnc-CASSNAT consists of only an encoder as the major module, which can be the SFM.
Non-uniform Speaker Disentanglement For Depression Detection From Raw Speech Signals
We find that a greater adversarial weight for the initial layers leads to performance improvement.
Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASR
With the proposed methods (E-APC and DRAFT), the relative WER improvements are even larger (30% and 19% on the OGI and MyST data, respectively) when compared to the models without using pretraining methods.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech Recognition
During inference, an error-based alignment sampling method is investigated in depth to reduce the alignment mismatch in the training and testing processes.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Learning from human perception to improve automatic speaker verification in style-mismatched conditions
Using the SITW evaluation tasks, which involve different conversational speech tasks, the proposed loss combined with self-attention conditioning results in significant relative improvements in EER by 2-5% and minDCF by 6-12% over baseline.
Attention-based conditioning methods using variable frame rate for style-robust speaker verification
However, self-attentive embeddings perform weighted pooling such that the weights correspond to the importance of the frames in a speaker classification task.
Unsupervised Instance Discriminative Learning for Depression Detection from Speech Signals
To learn instance-spread-out embeddings, we explore methods for sampling instances for a training batch (distinct speaker-based and random sampling).
A Step Towards Preserving Speakers' Identity While Detecting Depression Via Speaker Disentanglement
With adversarial training, depression classification improves for every feature when compared to the baseline.
DRAFT: A Novel Framework to Reduce Domain Shifting in Self-supervised Learning and Its Application to Children's ASR
However, models trained through SSL are biased to the pretraining data which is usually different from the data used in finetuning tasks, causing a domain shifting problem, and thus resulting in limited knowledge transfer.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Automatic Dialect Density Estimation for African American English
In this paper, we explore automatic prediction of dialect density of the African American English (AAE) dialect, where dialect density is defined as the percentage of words in an utterance that contain characteristics of the non-standard dialect.
Towards Better Meta-Initialization with Task Augmentation for Kindergarten-aged Speech Recognition
When data are scarce, the model might overfit to the training data, and hence good starting points for training are essential.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Can Social Robots Effectively Elicit Curiosity in STEM Topics from K-1 Students During Oral Assessments?
This paper presents the results of a pilot study that introduces social robots into kindergarten and first-grade classroom tasks.
LPC Augment: An LPC-Based ASR Data Augmentation Algorithm for Low and Zero-Resource Children's Dialects
This paper proposes a novel linear prediction coding-based data aug-mentation method for children's low and zero resource dialect ASR.
FrAUG: A Frame Rate Based Data Augmentation Method for Depression Detection from Speech Signals
The improvements for the CONVERGE (Mandarin) dataset when using the x-vector embeddings with CNN as the backend and MFCCs as input features were 9. 32% (validation) and 12. 99% (test).
Low Resource German ASR with Untranscribed Data Spoken by Non-native Children -- INTERSPEECH 2021 Shared Task SPAPL System
~ 5 hours of transcribed data and ~ 60 hours of untranscribed data are provided to develop a German ASR system for children.
An Improved Single Step Non-autoregressive Transformer for Automatic Speech Recognition
For the analyses, we plot attention weight distributions in the decoders to visualize the relationships between token-level acoustic embeddings.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Fundamental Frequency Feature Normalization and Data Augmentation for Child Speech Recognition
Because of the lack of publicly available young child speech data, feature extraction strategies such as feature normalization and data augmentation must be considered to successfully train child ASR systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR
We present a bidirectional unsupervised model pre-training (UPT) method and apply it to children's automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Analysis of Disfluency in Children's Speech
Disfluencies are prevalent in spontaneous speech, as shown in many studies of adult speech.
Variable frame rate-based data augmentation to handle speaking-style variability for automatic speaker verification
For instance, when enrolled with conversation utterances, the EER increased to 3. 03%, 2. 96% and 22. 12% when tested on read, narrative, and pet-directed speech, respectively.
Exploring the Use of an Unsupervised Autoregressive Model as a Shared Encoder for Text-Dependent Speaker Verification
A fusion of the x-vector/PLDA baseline and the SID/PLDA scores prior to PID fusion further improved performance by 15% indicating complementarity of the proposed approach to the x-vector system.
Speaker discrimination in humans and machines: Effects of speaking style variability
Native listeners performed better than machines in the style-matched conditions (EERs of 6. 96% versus 14. 35% for read speech, and 15. 12% versus 19. 87%, for conversations), but for style-mismatched conditions, there was no significant difference between native listeners and machines.
Glottal Source Processing: from Analysis to Applications
The great majority of current voice technology applications relies on acoustic features characterizing the vocal tract response, such as the widely used MFCC of LPC parameters.
Joint Robust Voicing Detection and Pitch Estimation Based on Residual Harmonics
This paper focuses on the problem of pitch tracking in noisy conditions.
Deep neural network based i-vector mapping for speaker verification using short utterances
Experimental results using the NIST SRE 2010 dataset show that both methods provide significant improvement and result in a max of 28. 43% relative improvement in Equal Error Rates from a baseline system, when using deep encoder with residual blocks and adding an additional phoneme vector.
