Package rst.audition
Audio signal processing, sometimes referred to as audio processing,
is the intentional alteration of auditory signals, or sound.
This package contains data type definitions related to audio
processing.
Messages
digraph message_graph {
fontname="Arial";
fontsize=11;
stylesheet="../_static/graphs.css";
node [fontsize=11,fontname="Arial"]
edge [fontsize=11,fontname="Arial"]
"5" [label=<<TABLE BORDER="0"><TR><TD COLSPAN="2" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk" TITLE="Structure rst.audition.SoundChunk" TARGET="_parent"><TABLE BORDER="0"><TR><TD ALIGN="right"><IMG SRC="../_static/message.svg"></IMG></TD><TD ALIGN="left">SoundChunk</TD></TR></TABLE></TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-__rosetta-OCTET-VECTOR.html#OCTET-VECTOR" TITLE="Fundamental OCTET-VECTOR" TARGET="_parent">OCTET-VECTOR</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.data" TITLE="Field rst.audition.SoundChunk.data" TARGET="_parent" PORT="data">data</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-__rosetta-UINT32.html#UINT32" TITLE="Fundamental UINT32" TARGET="_parent">UINT32</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.sample_count" TITLE="Field rst.audition.SoundChunk.sample_count" TARGET="_parent" PORT="sample_count">sample_count</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-__rosetta-UINT32.html#UINT32" TITLE="Fundamental UINT32" TARGET="_parent">UINT32</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.channels" TITLE="Field rst.audition.SoundChunk.channels" TARGET="_parent" PORT="channels">channels</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-__rosetta-UINT32.html#UINT32" TITLE="Fundamental UINT32" TARGET="_parent">UINT32</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.rate" TITLE="Field rst.audition.SoundChunk.rate" TARGET="_parent" PORT="rate">rate</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType" TITLE="Enum rst.audition.SoundChunk.SampleType" TARGET="_parent">SampleType</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.sample_type" TITLE="Field rst.audition.SoundChunk.sample_type" TARGET="_parent" PORT="sample_type">sample_type</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.EndianNess" TITLE="Enum rst.audition.SoundChunk.EndianNess" TARGET="_parent">EndianNess</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.endianness" TITLE="Field rst.audition.SoundChunk.endianness" TARGET="_parent" PORT="endianness">endianness</TD></TR></TABLE>>,shape=box,style=filled,fillcolor="white"];
"7" [label=<<TABLE BORDER="0"><TR><TD COLSPAN="2" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.EndianNess" TITLE="Enum rst.audition.SoundChunk.EndianNess" TARGET="_parent"><TABLE BORDER="0"><TR><TD ALIGN="right"><IMG SRC="../_static/enum.svg"></IMG></TD><TD ALIGN="left">EndianNess</TD></TR></TABLE></TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.EndianNess.ENDIAN_LITTLE" TITLE="Value rst.audition.SoundChunk.EndianNess.ENDIAN_LITTLE" TARGET="_parent">ENDIAN_LITTLE</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.EndianNess.ENDIAN_LITTLE" TITLE="Value rst.audition.SoundChunk.EndianNess.ENDIAN_LITTLE" TARGET="_parent">0</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.EndianNess.ENDIAN_BIG" TITLE="Value rst.audition.SoundChunk.EndianNess.ENDIAN_BIG" TARGET="_parent">ENDIAN_BIG</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.EndianNess.ENDIAN_BIG" TITLE="Value rst.audition.SoundChunk.EndianNess.ENDIAN_BIG" TARGET="_parent">1</TD></TR></TABLE>>,shape=box,style=filled,fillcolor="white"];
"6" [label=<<TABLE BORDER="0"><TR><TD COLSPAN="2" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType" TITLE="Enum rst.audition.SoundChunk.SampleType" TARGET="_parent"><TABLE BORDER="0"><TR><TD ALIGN="right"><IMG SRC="../_static/enum.svg"></IMG></TD><TD ALIGN="left">SampleType</TD></TR></TABLE></TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_S8" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_S8" TARGET="_parent">SAMPLE_S8</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_S8" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_S8" TARGET="_parent">0</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_U8" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_U8" TARGET="_parent">SAMPLE_U8</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_U8" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_U8" TARGET="_parent">1</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_S16" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_S16" TARGET="_parent">SAMPLE_S16</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_S16" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_S16" TARGET="_parent">2</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_U16" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_U16" TARGET="_parent">SAMPLE_U16</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_U16" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_U16" TARGET="_parent">4</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_S24" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_S24" TARGET="_parent">SAMPLE_S24</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_S24" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_S24" TARGET="_parent">8</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_U24" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_U24" TARGET="_parent">SAMPLE_U24</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.SoundChunk.SampleType.SAMPLE_U24" TITLE="Value rst.audition.SoundChunk.SampleType.SAMPLE_U24" TARGET="_parent">16</TD></TR></TABLE>>,shape=box,style=filled,fillcolor="white"];
"4" [label=<<TABLE BORDER="0"><TR><TD COLSPAN="2" HREF="../generated/stable/package-rst-audition.html#rst.audition.InterauralTimeDifference" TITLE="Structure rst.audition.InterauralTimeDifference" TARGET="_parent"><TABLE BORDER="0"><TR><TD ALIGN="right"><IMG SRC="../_static/message.svg"></IMG></TD><TD ALIGN="left">InterauralTimeDifference</TD></TR></TABLE></TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-__rosetta-FLOAT32.html#FLOAT32" TITLE="Fundamental FLOAT32" TARGET="_parent">FLOAT32</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.InterauralTimeDifference.value" TITLE="Field rst.audition.InterauralTimeDifference.value" TARGET="_parent" PORT="value">value</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-__rosetta-FLOAT32.html#FLOAT32" TITLE="Fundamental FLOAT32" TARGET="_parent">FLOAT32</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.InterauralTimeDifference.weight" TITLE="Field rst.audition.InterauralTimeDifference.weight" TARGET="_parent" PORT="weight">weight</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-__rosetta-FLOAT32.html#FLOAT32" TITLE="Fundamental FLOAT32" TARGET="_parent">FLOAT32</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.InterauralTimeDifference.frame_shift" TITLE="Field rst.audition.InterauralTimeDifference.frame_shift" TARGET="_parent" PORT="frame_shift">frame_shift</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-__rosetta-FLOAT32.html#FLOAT32" TITLE="Fundamental FLOAT32" TARGET="_parent">FLOAT32</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.InterauralTimeDifference.time_window" TITLE="Field rst.audition.InterauralTimeDifference.time_window" TARGET="_parent" PORT="time_window">time_window</TD></TR></TABLE>>,shape=box,style=filled,fillcolor="white"];
"1" [label=<<TABLE BORDER="0"><TR><TD COLSPAN="2" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk" TITLE="Structure rst.audition.FormattedSoundChunk" TARGET="_parent"><TABLE BORDER="0"><TR><TD ALIGN="right"><IMG SRC="../_static/message.svg"></IMG></TD><TD ALIGN="left">FormattedSoundChunk</TD></TR></TABLE></TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.FloatSoundArray" TITLE="Structure rst.audition.FloatSoundArray" TARGET="_parent">FloatSoundArray</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.data" TITLE="Field rst.audition.FormattedSoundChunk.data" TARGET="_parent" PORT="data">data</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-__rosetta-UINT32.html#UINT32" TITLE="Fundamental UINT32" TARGET="_parent">UINT32</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.rate" TITLE="Field rst.audition.FormattedSoundChunk.rate" TARGET="_parent" PORT="rate">rate</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-__rosetta-UINT32.html#UINT32" TITLE="Fundamental UINT32" TARGET="_parent">UINT32</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.channels" TITLE="Field rst.audition.FormattedSoundChunk.channels" TARGET="_parent" PORT="channels">channels</TD></TR></TABLE>>,shape=box,style=filled,fillcolor="white"];
"3" [label=<<TABLE BORDER="0"><TR><TD COLSPAN="2" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.ChannelType" TITLE="Enum rst.audition.FormattedSoundChunk.ChannelType" TARGET="_parent"><TABLE BORDER="0"><TR><TD ALIGN="right"><IMG SRC="../_static/enum.svg"></IMG></TD><TD ALIGN="left">ChannelType</TD></TR></TABLE></TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.ChannelType.ALL" TITLE="Value rst.audition.FormattedSoundChunk.ChannelType.ALL" TARGET="_parent">ALL</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.ChannelType.ALL" TITLE="Value rst.audition.FormattedSoundChunk.ChannelType.ALL" TARGET="_parent">0</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.ChannelType.LEFT" TITLE="Value rst.audition.FormattedSoundChunk.ChannelType.LEFT" TARGET="_parent">LEFT</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.ChannelType.LEFT" TITLE="Value rst.audition.FormattedSoundChunk.ChannelType.LEFT" TARGET="_parent">1</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.ChannelType.RIGHT" TITLE="Value rst.audition.FormattedSoundChunk.ChannelType.RIGHT" TARGET="_parent">RIGHT</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.ChannelType.RIGHT" TITLE="Value rst.audition.FormattedSoundChunk.ChannelType.RIGHT" TARGET="_parent">2</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.ChannelType.FRONT" TITLE="Value rst.audition.FormattedSoundChunk.ChannelType.FRONT" TARGET="_parent">FRONT</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.ChannelType.FRONT" TITLE="Value rst.audition.FormattedSoundChunk.ChannelType.FRONT" TARGET="_parent">3</TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.ChannelType.REAR" TITLE="Value rst.audition.FormattedSoundChunk.ChannelType.REAR" TARGET="_parent">REAR</TD><TD ALIGN="right" HREF="../generated/stable/package-rst-audition.html#rst.audition.FormattedSoundChunk.ChannelType.REAR" TITLE="Value rst.audition.FormattedSoundChunk.ChannelType.REAR" TARGET="_parent">4</TD></TR></TABLE>>,shape=box,style=filled,fillcolor="white"];
"2" [label=<<TABLE BORDER="0"><TR><TD COLSPAN="2" HREF="../generated/stable/package-rst-audition.html#rst.audition.FloatSoundArray" TITLE="Structure rst.audition.FloatSoundArray" TARGET="_parent"><TABLE BORDER="0"><TR><TD ALIGN="right"><IMG SRC="../_static/message.svg"></IMG></TD><TD ALIGN="left">FloatSoundArray</TD></TR></TABLE></TD></TR><TR><TD ALIGN="left" HREF="../generated/stable/package-__rosetta-FLOAT32.html#FLOAT32" TITLE="Fundamental FLOAT32" TARGET="_parent">FLOAT32</TD><TD ALIGN="left" HREF="../generated/stable/package-rst-audition.html#rst.audition.FloatSoundArray.floatbuffer" TITLE="Field rst.audition.FloatSoundArray.floatbuffer" TARGET="_parent" PORT="floatbuffer">floatbuffer</TD></TR></TABLE>>,shape=box,style=filled,fillcolor="white"];
"5" -> "7" [];
"5" -> "6" [];
"5":endianness -> "7" [];
"5":sample_type -> "6" [];
"1" -> "3" [];
"1":data -> "2" [];
}
clearer: should be made invisible via css
Message FloatSoundArray
class rst.audition.
FloatSoundArray
Deinterleaved float array needed by audiocues component
Todo
what is a deinterleaved float array?
Code author: Antoine Deleforge <antoine. deleforge@ inrialpes. fr >
floatbuffer
Unit : TODO
TODO
Download this file
message FloatSoundArray {
/**
* TODO
*/
// @unit(TODO)
repeated float floatbuffer = 1 ;
};
Message InterauralTimeDifference
class rst.audition.
InterauralTimeDifference
Constraint : len(.value) = len(.weight)
Interaural time difference measurements.
Code author: TODO Vasil <Khalidov>
<vasil. khalidov@ idiap. ch >
value
Unit : seconds
TODO ITD values
weight
Constraint : sum to 1
Constraint : 0 <= value <= 1
Unit : number
TODO Weights of the ITD value
frame_shift
Unit : second
TODO Frame shift between time windows
time_window
Unit : second
Length of the time window to compute an ITD value.
Download this file
message InterauralTimeDifference {
/**
* TODO ITD values
*/
// @unit(seconds)
repeated float value = 1 ;
/**
* TODO Weights of the ITD value
*/
// @constraint(sum to 1)
// @constraint(0 <= value <= 1)
// @unit(number)
repeated float weight = 2 ;
/**
* TODO Frame shift between time windows
*/
// @unit(second)
required float frame_shift = 3 ;
/**
* Length of the time window to compute an ITD value.
*/
// @unit(second)
required float time_window = 4 ;
}
Message SoundChunk
class rst.audition.
SoundChunk
Constraint : len(.data) == 8 * .channels * .sample_count * TODO(.sample_type)
Objects of this represent a chunk of an audio stream.
The audio information for one or more channels
is stored in
data
as a sequence of sample_count
encoded samples, the
encoding of which is described by endianness
and sample_type
.
Depending on the sample rate (rate
), such a chunk of audio
corresponds to a certain amount of time during which its samples
have been recorded.
Interpretation of RSB timestamps:
create:
Capture time of the audio buffer. More precisely, the
timestamp should correspond to the first sample contained
in the buffer.
Code author: David Klotz <dklotz@ techfak. uni-bielefeld. de >
data
TODO
sample_count
Unit : number
TODO
channels
Unit : number
TODO
rate
Unit : hz
TODO
sample_type
TODO
endianness
TODO
Download this file
message SoundChunk {
/**
* TODO
*/
enum SampleType {
/**
* Signed 8-bit samples.
*/
SAMPLE_S8 = 0 ;
/**
* Unsigned 8-bit samples.
*/
SAMPLE_U8 = 1 ;
/**
* Signed 16-bit samples.
*/
SAMPLE_S16 = 2 ;
/**
* Unsigned 16-bit samples.
*/
SAMPLE_U16 = 4 ;
/**
* Signed 24-bit samples.
*/
SAMPLE_S24 = 8 ;
/**
* Unsigned 24-bit samples.
*/
SAMPLE_U24 = 16 ;
}
/**
* TODO
*/
enum EndianNess {
ENDIAN_LITTLE = 0 ;
ENDIAN_BIG = 1 ;
}
/**
* TODO
*/
required bytes data = 1 ;
/**
* TODO
*/
// @unit(number)
required uint32 sample_count = 2 ;
/**
* TODO
*/
// @unit(number)
optional uint32 channels = 3 [ default = 1 ];
/**
* TODO
*/
// @unit(hz)
optional uint32 rate = 4 [ default = 44100 ];
/**
* TODO
*/
optional SampleType sample_type = 5 [ default = SAMPLE_S16 ];
/**
* TODO
*/
optional EndianNess endianness = 6 [ default = ENDIAN_LITTLE ];
// TODO: interleaving type?
}
Message SampleType
class rst.audition.SoundChunk.
SampleType
TODO
SAMPLE_S8
= 0
Signed 8-bit samples.
SAMPLE_U8
= 1
Unsigned 8-bit samples.
SAMPLE_S16
= 2
Signed 16-bit samples.
SAMPLE_U16
= 4
Unsigned 16-bit samples.
SAMPLE_S24
= 8
Signed 24-bit samples.
SAMPLE_U24
= 16
Unsigned 24-bit samples.
Download this file
enum SampleType {
/**
* Signed 8-bit samples.
*/
SAMPLE_S8 = 0 ;
/**
* Unsigned 8-bit samples.
*/
SAMPLE_U8 = 1 ;
/**
* Signed 16-bit samples.
*/
SAMPLE_S16 = 2 ;
/**
* Unsigned 16-bit samples.
*/
SAMPLE_U16 = 4 ;
/**
* Signed 24-bit samples.
*/
SAMPLE_S24 = 8 ;
/**
* Unsigned 24-bit samples.
*/
SAMPLE_U24 = 16 ;
}
Message EndianNess
class rst.audition.SoundChunk.
EndianNess
TODO
ENDIAN_LITTLE
= 0
Not documented
ENDIAN_BIG
= 1
Not documented