Sharif Digital Repository

In this thesis, we investigate speaker verification as a biometric technology to verify a person based on his/her claim. Text-dependent speaker verification systems are preferred in commercial and security applications and these systems have better performance in limited data condition based on a prior knowledge about speakers that are assumed to be cooperative. Limited amount of enrollment data is a major concern in this thesis. Speaker dependent model construction and channel variability issues on telephone-based text-dependent speaker verification applications are surveyed. Due to the lack of an appropriate database for the task, we collected a database which is referred to as text-prompt... 

Today, the production of colloquial texts in messengers, search engines, and question and answer systems has increased significantly, while text documents in other fields have a formal tone and style. Thus, there is a need for a system to convert these texts from colloquial form to the formal style. Attention to this need in non-Persian languages has also been recently and seriously felt, but almost at the time of writing, an efficient system has not been offered, and this issue requires more work in Persian than in languages such as English. In general, transferring texts from one form to another falls into the category of natural language processing applications and is called "style... 

Quality and intelligibility are two aspects of speech that are affected by various factors, such as background noise and echo. The performance of many commercial and military speech-based systems depends on at least one of these aspects of speech. Therefore, this research aims to design an improvement model to remove background noise and reverberation from the speech signal. The model training framework is based on deep learning methods and has a supervised approach in the time domain. The input of this system is the raw waveform of the speech signal mixed with noise and reverberation, and the output is the enhanced waveform of this signal. An architecture is proposed in this thesis based on... 

In recent years, deep neural networks have achieved significant improvements in the field of automatic text summarization by using neural sequence architectures. However,the results of these improvements are more tangible in the production of short summaries (a few words or single sentences). In the field of producing long (multisentence) abstracts, the presented models suffer from several issues; These models produce the details of the events incorrectly and tend to generate the phrases been produced before repeatedly. The wording from the output of these models is very close to the original text. Also, the metrics used to evaluate the quality of produced summaries do not have the ability... 

Formality style transfer, in other words, automatic transfering style of informal text to formal and vice versa, means changing the style and form of a sentence without changing its content. With the increasing progress of deep neural networks, the formality style transfer in other languages has attracted the attention of other researchers and has made significant progress in natural language processing tasks. Due to the availability of parallel data in the English language, the task of style transfer has been approached and designed basically in the framework of the "encoder-decoder" architecture of neural networks. However, due to the lack of parallel datasets in the Persian language, this... 

Automatic recognition of musical Maqams has been one of the challenging problems in Music Information Retrieval. Despite the increasing amount of related research in recent years, we are still far away from building related real-life applications. Nevertheless, a very small portion of these research is dedicated to automatic recognition of Maqams in recitation of the Holy Quran. In this thesis, as a first attempt, we have used machine learning methods to classify six Maqam families which are commonly used in Quran recitation. Also, due to the lack of pre-exisiting datasets, we have annotated approximately 1325 minutes of Tadwir recitation from two prominent Egyptian reciters, i.e., Muhammad... 

This project has been conducted in two related phases: In the first phase, we have attempted to write a program capable of answering thematic similarity multiple-choice questions without utilizing any training data. The best performance in this phase was attained by the 25-topic LDA model using the Hellinger distance between the probability distributions of the poetic verses. This model managed to attain an accuracy of 42%, which is very close to the average human performance of 43%. In the second phase, two tasks of seven-class classification and binary classification were defined based on the p-value of the questions. To this end, the questions were initially ranked according to the... 

Diverse personal names are mentioned in everyday news but news agencies do not separate entities with same or equal names. This could make irrelevant news appear while searching an ambiguous name. Personal Name Disambiguation in news seeks to partition a significant amount of news to distinct classes each of which belongs to a single entity in the real world. In this thesis, which up to the researcher is the first of its kind at least in Persian, researcher gained opportunity of using FarsiYar News Dataset and to be specific 50,000 of news in FarsNews dataset which were published in the year 1397. First of all, a database was built using these news data and then the nonstructured news were... 

In recent years, word embeddings as the word representation have captured the attention of natural language processing (NLP) researches. One of the great advantages of word embeddings is their capability in representing the relationships of the words. Therefore, using word embeddings in NLP applications results in better performance.Despite widespread attention towards word embedding in late years, Persian word embeddings have not achieved sensible progress. One of the Persian word embeddings difficulties is related to that, Persian is a low-resource language in comparison with worldwide languages. Therefore, Persian word embedding quality is lower than English. Consequently, the accuracy of... 

Keyphrase extraction, as an important open problem of Natural Language Processing (NLP), is useful as a stand-alone task in the field of Information Extraction and as an upstream task for Information Retrieval, text summarization and classification,etc. In this study, regarding the needs in Persian NLP, artificial neural networks are adopted to extract keyphrases from single documents and a graph-based re-scoring method is proposed for multidocument keyphrase extraction. The proposed method for extracting keyphrases from multiple documents consists of two steps: (1) extracting keyphrases of each document in a cluster using a sequence to sequence model with attention, and (2) re-scoring the... 

This thesis examines the differences and the similarities between the two famous RNN blocks the Long Short Term Memory and the Gated Recurrent Unit. It measure different aspects such as computational complexity, Word Error Rate, and subjective human evaluation in the task of text generation.In the computational complexity experiment results show that the LSTM takes more time to compute, in comparison to the GRU. Moving on into the next experiment the GRU slightly outperforms the LSTM in terms of WER but the perplexity for the language models tested was the same. This shows that slight differences in the perplexity does not drastically change the WER. Having said, the results suggest that the... 

Relation extraction is known as a main task in information extraction. There are two main approach in this field, rule based and statistical approaches. This thesis applied a rule based relation extraction approach. In this research we tried to recognize Persian syntactic and morphological patterns to extract relation between named entities. At first we annotated a news dataset by person,organization and location named entity tags which is included more than 100 thousand tokens. After that we found there are 1037 relations 2197 candidate relations. Candidate and labled relations extracted between two entities which is located in a clause. These relations are "PERS_PERS-COMMENTING",... 

Spoken Language Understanding (SLU) is aimed at extracting meaning from natural spoken language. Meaning extraction ranges from "extracting specific phrases" to "extracting users' intentions from their speech" and goes as far as "extracting the entities and details of their intentions". Extracting the exact intended meaning of the user is a sophisticated process. In this research, considering the lack of standard data in Persian, an SLU system for this language has been implemented using Markov Logic Networks (MLNs), in order to reduce the need for extra datasets. MLNs combine the explanatory power and orderliness of First-Order Logic with the uncertainty of probabilities. Therefore, these... 

The stress positions of the words are determined according to the type of their morphological elements. Persian Words often have a fixed position for stress. However, Persian wordforms show different stress positions, based on their morpheme types or in the other words, their bound-non derivational affixes. Inflectional affixes accept stress, whereas clitics do not. In the present research we studied both types of non derivational affixes considering their phonetic features meaning fundamental frequency and duration. The phonetic representation of the pitch accent as the phonemic- intonational element was given as a result of this study, as well. The differences in the phonetic... 

This study is a research on Persian Intonational System, which was carried out within the Autosegmental-Metrical framework.The intonational elements of Persian are represented by two distinctive levels (High and Low). Persian intonation system enjoys three main elements: pitch accents, Phrase accents and boundary tones. Every intonational element has its own meaning. The data of study is about 200 utterances produced by two Persian native speaker one male and one female. These utterances have been annotated in four levels in PToBI: phoneme level, word level, tone level and break index level. In this study we aimed to formulate the acoustic representation of the intonational elements by three... 

Nowadays Artificial Intelligence systems are ubiquitous. One of the important applications is textual question-answering systems, which provide a means of information retrieval in a user-friendly manner. Reasoning is an inseparable part of human daily life, and people use reasoning to judge and find rational and correct answers to questions. To get the desired output from question-answering systems, these systems must be equipped with reasoning. This research focuses on improving question answering by considering Commonsense Reasoning. The two most important weaknesses of the existing question-answering systems are the questions being in the form of multiple-choice, which is far from a... 

In this thesis, we introduce a novel Artificial Intelligence (AI) system inspired by the philosophical and psychoanalytical concept of imagination as a ``Re-construction of Experiences". Our AI system is equipped with an imagination-inspired module that bridges the gap between textual inputs and other modalities, enriching the derived information based on previously learned experiences. A unique feature of our system is its ability to formulate independent perceptions of inputs. This leads to unique interpretations of a concept that may differ from human interpretations but are equally valid, a phenomenon we term as ``Interpretable Misunderstanding". We employ large-scale models,... 

Many Text-to-Speech (TTS) systems, particularly in low-resource environments, struggle to produce natural and intelligible speech from grapheme sequences. One solution to this problem is to use Grapheme-to-Phoneme (G2P) conversion to increase the information in the input sequence and improve the TTS output. However, current G2P systems are not accurate or efficient enough for Persian texts due to the language’s complexity and the lack of short vowels in Persian grapheme sequences. In our study, we aimed to improve resources for the Persian language. To achieve this, we introduced two new G2P training datasets, one manually-labeled and the other machine-generated, containing over five million... 

Conversational Question Answering (CQA) has gained significant attention in recent years due to its potential to facilitate natural language interactions between humans and machines. The ability to effectively incorporate relevant history turns, which are previous utterances in a conversation, plays a crucial role in improving the overall performance of CQA systems. In this master's thesis, we explore the importance of conversational question answering and propose a novel approach for selecting relevant history turns to enhance the accuracy and relevance of the system's responses. Initially, we provide an overview of the recent models developed for addressing the CQA challenge. We analyze... 

This thesis focuses on generating text from data. The Data-to-Text system must have three capabilities; First, it should be able to produce coherent, comprehensible, fluent text that is close to human natural language, in such a way that it is not possible to distinguish it from texts written by humans. Second, to be able to produce a variety of sentences to express the same concept. The third is to be able to express the information of the input data without repetition, redundancy, and omission in the output sentences. The latter is one of the main challenges of data-to-text systems because not being faithful to the input data can lead to se- rious problems in real-world applications. Until...