Search Results for author:
Found 42 papers, 9 papers with code
Speaker Verification Experiments for Adults and Children Using Shared Embedding Spaces
For children, the system trained on a large corpus of adult speakers performed worse than a system trained on a much smaller corpus of children’s speech.
Graph-based Syntactic Word Embeddings
We propose a simple and efficient framework to learn syntactic embeddings based on information derived from constituency parse trees.
Service registration chatbot: collecting and comparing dialogues from AMT workers and service’s users
In this article, we compare two crowdsourcing sources on a dialogue paraphrasing task revolving around a chatbot service.
Grapheme-Based Cross-Language Forced Alignment: Results with Uralic Languages
Forced alignment is an effective process to speed up linguistic research.
Spectral modification for recognition of children’s speech undermismatched conditions
The proposed method is used to improve the speech intelligibility to enhance the children’s speech recognition using an acoustic model trained on adult speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Semiautomatic Speech Alignment for Under-Resourced Languages
Cross-language forced alignment is a solution for linguists who create speech corpora for very low-resource languages.
Morfessor-enriched features and multilingual training for canonical morphological segmentation
Our approach is to pre-segment the input data for a neural sequence-to-sequence model with the unsupervised method.
When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity
Our results show that the model is capable of correctly detecting whether an utterance is humorous 78% of the time and how long the audience's laughter reaction should last with a mean absolute error of 600 milliseconds.
End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks
The current state-of-the-art methods proposed for these tasks are ensembles based on deep neural networks like ResNets in conjunction with feature engineering.
Comparison and Analysis of New Curriculum Criteria for End-to-End ASR
We hypothesize that end-to-end models can achieve better performance when provided with an organized training set consisting of examples that exhibit an increasing level of difficulty (i. e. a curriculum).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Finnish Parliament ASR corpus - Analysis, benchmarks and statistics
We set benchmarks on the official test sets, as well as multiple other recently used test sets.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks
The Donate Speech campaign has so far succeeded in gathering approximately 3600 hours of ordinary, colloquial Finnish speech into the Lahjoita puhetta (Donate Speech) corpus.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Data augmentation using prosody and false starts to recognize non-native children's speech
Firstly, we apply the prosody-based data augmentation to supplement the audio data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
FinChat: Corpus and evaluation setup for Finnish chat conversations on everyday topics
Using this corpus, we also construct a retrieval-based evaluation task for Finnish chatbot development.
Aalto's End-to-End DNN systems for the INTERSPEECH 2020 Computational Paralinguistics Challenge
On ComParE 2020 tasks, we investigate applying an ensemble of E2E models for robust performance and developing task-specific modifications for each task.
Effects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language Models
We, however, show that for character-based NNLMs, only pretraining with a related language improves the ASR performance, and using an unrelated language may deteriorate it.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Subword RNNLM Approximations for Out-Of-Vocabulary Keyword Search
On these tasks, interpolating the baseline RNNLM approximation and a conventional LM outperforms the conventional LM in terms of the Maximum Term Weighted Value for single-character subwords.
Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation
There are several approaches for improving neural machine translation for low-resource languages: Monolingual data can be exploited via pretraining or data augmentation; Parallel corpora on related language pairs can be used via parameter sharing or transfer learning in multilingual models; Subword segmentation and regularization techniques can be applied to ensure high coverage of the vocabulary.
Finnish Language Modeling with Deep Transformer Models
Transformers have recently taken the center stage in language modeling after LSTM's were considered the dominant model architecture for a long time.
Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning
Using English, Finnish, North Sami, and Turkish data sets, we show that this approach is able to find better solutions to the optimization problem defined by the Morfessor Baseline model than its original recursive training algorithm.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
A user study to compare two conversational assistants designed for people with hearing impairments
In the mobile device, augmented reality (AR) was used to help the hearing impaired observe gestures and lip movements of the speaker simultaneously with the transcriptions.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
The MeMAD Submission to the IWSLT 2018 Speech Translation Task
In this paper, we also describe the experiments leading up to our final systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Cognate-aware morphological segmentation for multilingual neural translation
This article describes the Aalto University entry to the WMT18 News Translation Shared Task.
The MeMAD Submission to the WMT18 Multimodal Translation Task
Our experiments show that the effect of the visual features in our system is small.
Automatic Speech Recognition with Very Large Conversational Finnish and Estonian Vocabularies
Today, the vocabulary size for language models in large vocabulary speech recognition is typically several hundreds of thousands of words.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
TheanoLM - An Extensible Toolkit for Neural Network Language Modeling
We present a new tool for training neural network language models (NNLMs), scoring sentences, and generating text.
English Conversational Speech Recognition
Language Modelling
+1
A Toolkit for Efficient Learning of Lexical Units for Speech Recognition
String segmentation is an important and recurring problem in natural language processing and other domains.
